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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 42136
    Prev
    Next
    INDEX
    Explanations

    plant reproduction

    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_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
     meaningful
    -0.06
    #af
    -0.06
    wipe
    -0.06
     chess
    -0.06
    油气
    -0.06
     LAT
    -0.06
     convex
    -0.06
     Fiat
    -0.06
    契
    -0.06
     pirate
    -0.06
    POSITIVE LOGITS
    cols
    0.09
    /entities
    0.08
    idades
    0.08
    mutation
    0.07
     Arrival
    0.07
    /#{
    0.07
    _PRODUCTS
    0.07
    لد
    0.07
    *=
    0.07
    니까
    0.07
    Activations Density 0.001%

    No Known Activations