© 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. 77908
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     인
    -0.07
    Wil
    -0.07
     lamin
    -0.07
     psy
    -0.07
     Schl
    -0.07
    (database
    -0.06
    -sw
    -0.06
     Holidays
    -0.06
     SNAP
    -0.06
     probabil
    -0.06
    POSITIVE LOGITS
    dling
    0.07
    CELER
    0.07
     Does
    0.07
    وس
    0.07
     Grande
    0.07
    .getWindow
    0.07
    太
    0.06
    عار
    0.06
    ikel
    0.06
    Demand
    0.06
    Activations Density 0.012%

    No Known Activations