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. 41606
    Prev
    Next
    INDEX
    Explanations

    Parts

    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
    _up
    -0.07
     blockade
    -0.07
    FieldValue
    -0.07
     oleh
    -0.07
     Sue
    -0.07
    ılan
    -0.07
    ி�
    -0.07
    马来西亚
    -0.07
     الصادر
    -0.07
    .Serializer
    -0.06
    POSITIVE LOGITS
    (debug
    0.08
     UTF
    0.07
    =utf
    0.07
    =num
    0.07
    ecn
    0.07
     %%↵
    0.07
    _BLUE
    0.07
     Pruitt
    0.07
     VERIFY
    0.07
    内衣
    0.07
    Activations Density 0.087%

    No Known Activations