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. 72953
    Prev
    Next
    INDEX
    Explanations

    Real estate/financial transactions

    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
    ymmetric
    -0.26
    estone
    -0.26
     breadcrumbs
    -0.26
    ä¸įæĪIJ
    -0.25
    çĿģ
    -0.25
    ioned
    -0.25
    æı¡
    -0.24
    eeper
    -0.24
    è¿ĩçļĦ
    -0.24
    æŀķ头
    -0.24
    POSITIVE LOGITS
    ï¸
    0.28
    kins
    0.26
     hilar
    0.25
     final
    0.25
    era
    0.25
    final
    0.25
    ãĤŃãĥ³
    0.25
     console
    0.24
    console
    0.24
    E
    0.24
    Activations Density 0.007%

    No Known Activations