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. 130633
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    .extract
    -0.07
    responses
    -0.07
     corridors
    -0.07
    goods
    -0.07
    _that
    -0.07
     chromium
    -0.07
    科协
    -0.07
    谢谢
    -0.06
    源源不断
    -0.06
    setError
    -0.06
    POSITIVE LOGITS
    union
    0.08
     وم
    0.07
    变换
    0.07
    袭击
    0.07
    phasis
    0.06
    管制
    0.06
    逵
    0.06
     gamb
    0.06
    ertura
    0.06
     cath
    0.06
    Activations Density 0.001%

    No Known Activations