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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 53797
    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
     Ole
    -0.08
    蘩
    -0.07
     verschiedene
    -0.07
     Telephone
    -0.07
     Nhiều
    -0.07
    .vote
    -0.07
    四种
    -0.07
     poste
    -0.07
    いう
    -0.07
     favourites
    -0.07
    POSITIVE LOGITS
     ringing
    0.08
     продукции
    0.07
    clin
    0.07
    液
    0.07
    ―
    0.07
    smooth
    0.07
    asta
    0.06
    水平
    0.06
     misconduct
    0.06
    uniq
    0.06
    Activations Density 0.254%

    No Known Activations