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. 29893
    Prev
    Next
    INDEX
    Explanations

    boron

    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
    Images
    -0.07
     fantast
    -0.07
    촣
    -0.06
     Sunshine
    -0.06
     include
    -0.06
    ذلك
    -0.06
    ウォー
    -0.06
     Movies
    -0.06
    旅遊
    -0.06
     ghost
    -0.06
    POSITIVE LOGITS
     literal
    0.08
    _CAN
    0.07
    (bin
    0.07
     literals
    0.07
    insics
    0.07
    믜
    0.07
     complic
    0.07
    🔃
    0.06
     liberalism
    0.06
     relic
    0.06
    Activations Density 0.004%

    No Known Activations