© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 8672
    Prev
    Next
    INDEX
    Explanations

    technical instructions

    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
    statement
    -0.29
    mes
    -0.27
    anh
    -0.27
    _statement
    -0.26
    rase
    -0.26
     statement
    -0.26
    pecific
    -0.24
    è¶Ĭå¤ļ
    -0.24
    aring
    -0.24
    resenter
    -0.24
    POSITIVE LOGITS
    ISC
    0.28
    ÑģÑĥд
    0.28
    TED
    0.27
     downward
    0.25
     careful
    0.25
    екÑĤ
    0.25
     tú
    0.24
    .shtml
    0.24
    icare
    0.24
     Manual
    0.24
    Activations Density 0.019%

    No Known Activations