Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 61768
    Prev
    Next
    INDEX
    Explanations

    stew

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     год
    -0.09
     mots
    -0.08
    etsy
    -0.07
    çon
    -0.07
    .isBlank
    -0.07
    веч
    -0.07
    InputStream
    -0.06
     NBC
    -0.06
    .office
    -0.06
     нем
    -0.06
    POSITIVE LOGITS
     Physiology
    0.08
    摆在
    0.07
    游览
    0.07
    饮用
    0.07
    Groups
    0.07
    _stream
    0.07
    等症状
    0.07
    شعوب
    0.07
     Political
    0.07
    user
    0.06
    Activations Density 0.001%

    No Known Activations