© 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. 64652
    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
     helped
    -0.08
     providing
    -0.08
    沿着
    -0.07
    מב
    -0.07
    栏
    -0.07
     left
    -0.07
    𬺈
    -0.07
     vedere
    -0.07
     regulating
    -0.07
    加快
    -0.07
    POSITIVE LOGITS
     numa
    0.07
    民居
    0.07
     nouve
    0.06
    Issuer
    0.06
     ámbito
    0.06
    ’un
    0.06
    方位
    0.06
    Spo
    0.06
    过大
    0.06
    (Point
    0.06
    Activations Density 1.501%

    No Known Activations