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. 19-RESID-POST-AA
    6. 89297
    Prev
    Next
    INDEX
    Explanations

    Code and file paths

    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
    鹝
    -0.07
    뛔
    -0.07
    räu
    -0.07
     ידי
    -0.07
     Uniform
    -0.07
    뚤
    -0.07
    \Array
    -0.07
    wald
    -0.06
    𬶐
    -0.06
     voks
    -0.06
    POSITIVE LOGITS
    !=
    0.08
    빌
    0.08
     noteworthy
    0.08
    chain
    0.07
     секрет
    0.07
     divisible
    0.07
    */)↵
    0.07
     Glacier
    0.07
    .Visible
    0.07
    :null
    0.07
    Activations Density 0.000%

    No Known Activations