© 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. 60108
    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
    בשר
    -0.08
    ໃ
    -0.07
    梌
    -0.07
     этому
    -0.07
    تأسيس
    -0.07
    istributor
    -0.07
    معايير
    -0.07
    HttpClient
    -0.07
    événement
    -0.07
    equip
    -0.07
    POSITIVE LOGITS
     IMAGE
    0.08
    Returned
    0.07
    .Modules
    0.07
     illumin
    0.07
    只是为了
    0.07
    .Fields
    0.07
    .clientHeight
    0.07
    lü
    0.07
     trì
    0.07
     Er
    0.07
    Activations Density 0.001%

    No Known Activations