© 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. 8299
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    åĩºåı°
    -0.28
    线ä¸Ĭ
    -0.27
    æĽ´å¤ļ精彩
    -0.27
     zro
    -0.26
    estone
    -0.25
    ibase
    -0.25
    åIJİæİĴ
    -0.25
    .']
    -0.25
    veau
    -0.25
    æŃ£åĵģ
    -0.24
    POSITIVE LOGITS
    _
    0.30
     char
    0.29
    ole
    0.28
    UP
    0.28
     qu
    0.28
    åĨ³å®ļ
    0.27
    el
    0.27
    ost
    0.26
     cut
    0.26
     dur
    0.26
    Activations Density 0.026%

    No Known Activations