© 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. 11-RESID-POST-AA
    11. 22206
    Prev
    Next
    INDEX
    Explanations

    actions, movement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    研究所
    -0.07
    anium
    -0.07
    发展规划
    -0.07
     Tahoe
    -0.07
     {}.
    -0.07
    ailand
    -0.07
    نموذج
    -0.07
    そう
    -0.06
    ften
    -0.06
     géné
    -0.06
    POSITIVE LOGITS
    (bottom
    0.09
    就诊
    0.08
    Peer
    0.07
    被迫
    0.07
    暵
    0.07
     sorted
    0.07
    ination
    0.07
    璬
    0.07
    mal
    0.07
    _GPS
    0.07
    Activations Density 0.276%

    No Known Activations