© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 62525
    Prev
    Next
    INDEX
    Explanations

    The neuron detects mentions of forests or forest-related terms (references to the concept of "forest") in the text.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    宜
    -0.07
     distant
    -0.07
    UTURE
    -0.07
     piping
    -0.07
    UEL
    -0.07
    ucks
    -0.07
    惘
    -0.07
    .angle
    -0.07
     Bike
    -0.07
    secutive
    -0.07
    POSITIVE LOGITS
     forest
    0.08
     forests
    0.08
    格將
    0.07
     seriously
    0.07
    .setRotation
    0.07
     фор
    0.07
     formation
    0.07
    getContext
    0.07
    psz
    0.07
    מכון
    0.06
    Activations Density 0.010%

    No Known Activations