© 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. 8350
    Prev
    Next
    INDEX
    Explanations

    court documents

    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
    UF
    -0.26
    unner
    -0.26
     Bend
    -0.25
    åij¨äºĮ
    -0.25
     undoubtedly
    -0.24
    ä¸ĩæĪ·
    -0.24
    <article
    -0.24
     ÑĢÑıд
    -0.24
    æľīä¸Ģå®ļ
    -0.24
    -ing
    -0.24
    POSITIVE LOGITS
    езн
    0.26
    estar
    0.26
    posix
    0.26
    åı¬åĽŀ
    0.26
    éal
    0.26
    ajaran
    0.25
    locator
    0.24
    _print
    0.24
    iances
    0.24
    restrial
    0.24
    Activations Density 0.020%

    No Known Activations