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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 19-RESID-POST-AA
    6. 71243
    Prev
    Next
    INDEX
    Explanations

    IT

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .history
    -0.08
     emerge
    -0.07
    issen
    -0.06
     información
    -0.06
     Commerce
    -0.06
     **)&
    -0.06
     từ
    -0.06
     sofas
    -0.06
     kin
    -0.06
     );↵↵↵
    -0.06
    POSITIVE LOGITS
    녹
    0.08
    所在的
    0.08
    -eng
    0.07
     antic
    0.07
    治疗
    0.07
     Sly
    0.07
    REG
    0.07
    Closing
    0.07
    				           
    0.07
    ean
    0.07
    Activations Density 0.001%

    No Known Activations