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. 88209
    Prev
    Next
    INDEX
    Explanations

    Type / Target

    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
    阶段
    -0.07
     warm
    -0.07
    obbled
    -0.06
     unmanned
    -0.06
    ìn
    -0.06
    ڤ
    -0.06
    [count
    -0.06
    𝓯
    -0.06
    之初
    -0.06
    plate
    -0.06
    POSITIVE LOGITS
    יצע
    0.07
    -sales
    0.07
    实木
    0.07
    (recipe
    0.07
    .realm
    0.07
    を利用して
    0.07
    емые
    0.07
    一起装修
    0.07
    ита
    0.07
    حافظ
    0.07
    Activations Density 0.004%

    No Known Activations