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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 36072
    Prev
    Next
    INDEX
    Explanations

    Reviews, patterns, and directions

    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
    互联网
    -0.09
     zun
    -0.07
    _way
    -0.07
     touchdown
    -0.07
    再造
    -0.07
    آثار
    -0.07
    二十年
    -0.06
    👞
    -0.06
    �
    -0.06
    ))/(
    -0.06
    POSITIVE LOGITS
    staking
    0.07
    딕
    0.07
     ($)
    0.07
    _unique
    0.07
    $this
    0.07
    pitch
    0.07
    สเต
    0.07
    Bundle
    0.07
    ",
    ↵
    0.07
    �ん
    0.06
    Activations Density 0.003%

    No Known Activations