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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15-RESID-POST-AA
    6. 49462
    Prev
    Next
    INDEX
    Explanations

    taxes and financial topics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vực
    -0.07
     broadly
    -0.07
    切实
    -0.07
     luận
    -0.07
    个国家
    -0.06
     товаров
    -0.06
     ideally
    -0.06
    filePath
    -0.06
    ("/");↵
    -0.06
    _grupo
    -0.06
    POSITIVE LOGITS
    导
    0.08
    -online
    0.07
    .setFill
    0.07
     Colors
    0.07
    _SWITCH
    0.07
    _freq
    0.07
    IRM
    0.07
    illet
    0.07
    .MODEL
    0.07
     fuller
    0.07
    Activations Density 0.056%

    No Known Activations