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. 24543
    Prev
    Next
    INDEX
    Explanations

    lign

    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
    绝佳
    -0.07
    库里
    -0.07
    暢
    -0.07
    omy
    -0.07
    .SubItems
    -0.07
    __()
    -0.06
     cables
    -0.06
    .getvalue
    -0.06
     dives
    -0.06
    就说
    -0.06
    POSITIVE LOGITS
    对照
    0.07
    ,label
    0.07
     HK
    0.07
    ingroup
    0.06
    	help
    0.06
     overweight
    0.06
    dropdown
    0.06
    놐
    0.06
    .ACTION
    0.06
     pagina
    0.06
    Activations Density 0.002%

    No Known Activations