© 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. 8842
    Prev
    Next
    INDEX
    Explanations

    author

    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
    ä¸ĭåİ»
    -0.25
    maries
    -0.24
    è¡¥
    -0.24
    ancing
    -0.22
     HEADER
    -0.22
    ander
    -0.22
    FromString
    -0.21
    erson
    -0.21
    ON
    -0.21
    çģ¾
    -0.21
    POSITIVE LOGITS
    tá
    0.30
    edly
    0.24
    LAS
    0.24
    aar
    0.24
    icients
    0.24
    waitFor
    0.23
    ised
    0.23
    AES
    0.23
    aug
    0.23
    Tiny
    0.23
    Activations Density 1.590%

    No Known Activations