© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7510
    Prev
    Next
    INDEX
    Explanations

    review

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ropolis
    -0.27
    æľĪä¸ĭ
    -0.26
    adero
    -0.25
    ниÑĩ
    -0.25
    plement
    -0.25
    éĺµåľ°
    -0.25
     quarters
    -0.25
    Ô
    -0.25
    ä¸ĭåİ»
    -0.24
    ä¹ĭä¸ĭ
    -0.24
    POSITIVE LOGITS
    åĴ¨
    0.27
    _imm
    0.25
     gutter
    0.25
    管çIJĨç³»ç»Ł
    0.25
    keeper
    0.25
    è·³
    0.25
     winning
    0.24
    管çIJĨæĿ¡ä¾ĭ
    0.24
    isti
    0.24
    asher
    0.24
    Activations Density 0.062%

    No Known Activations