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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Qwen3-4B
    3. 11-TRANSCODER-HP
    4. 126004
    Prev
    Next
    INDEX
    Explanations

    financial

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_11.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.11.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çįŃ
    -0.29
    rán
    -0.27
     quotations
    -0.26
    esModule
    -0.25
    ationally
    -0.25
    éĩįä¸Ń
    -0.25
    Regional
    -0.25
    legt
    -0.25
    /cop
    -0.25
     XV
    -0.25
    POSITIVE LOGITS
    ither
    0.33
    orrh
    0.29
    alore
    0.27
    ive
    0.27
    ãn
    0.27
    Ø«ÙĦ
    0.27
    uez
    0.25
    ÙĨØ©
    0.25
    åĿ¦
    0.25
    kit
    0.25
    Activations Density 0.058%

    No Known Activations