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. 2820
    Prev
    Next
    INDEX
    Explanations

    programming

    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
    Ṩ
    -0.07
    ŵ
    -0.07
    urv
    -0.07
    9
    -0.07
    *p
    -0.06
    Figure
    -0.06
    面试
    -0.06
     rootNode
    -0.06
     TS
    -0.06
    (evt
    -0.06
    POSITIVE LOGITS
     Left
    0.09
    มงคล
    0.07
    _PROGRAM
    0.07
     Magical
    0.06
    ACY
    0.06
    有一些
    0.06
    互利
    0.06
    .ONE
    0.06
    谗
    0.06
    兢
    0.06
    Activations Density 0.390%

    No Known Activations