© 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. 9023
    Prev
    Next
    INDEX
    Explanations

    if

    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
    iji
    -0.30
     sobie
    -0.28
    è°
    -0.27
    å¼¹
    -0.26
     absorbing
    -0.26
    è°£
    -0.25
     Ade
    -0.25
    ivalence
    -0.25
     plausible
    -0.24
    _RENDERER
    -0.24
    POSITIVE LOGITS
    oci
    0.26
    åĻ¨
    0.26
    éªĦåĤ²
    0.25
    roys
    0.25
    cest
    0.25
    éģģ
    0.24
    nonce
    0.24
     rar
    0.24
     agency
    0.24
     Agency
    0.23
    Activations Density 0.044%

    No Known Activations