© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 77430
    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
     long
    -0.07
    Cleanup
    -0.06
     happy
    -0.06
    .System
    -0.06
    .insertBefore
    -0.06
     budget
    -0.06
     valu
    -0.06
    ,↵↵↵↵
    -0.06
    <a
    -0.06
     Stand
    -0.06
    POSITIVE LOGITS
    EDITOR
    0.07
    ubes
    0.07
    trägt
    0.07
    .copyWith
    0.07
    いった
    0.07
    encrypt
    0.06
     enviado
    0.06
    排毒
    0.06
     veut
    0.06
     Investigators
    0.06
    Activations Density 0.038%

    No Known Activations