© 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. 7788
    Prev
    Next
    INDEX
    Explanations

    Descriptions or introductions

    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
     diamond
    -0.24
    odox
    -0.24
     /**<
    -0.24
     tackles
    -0.24
    awi
    -0.23
    avi
    -0.23
    åĮª
    -0.23
    å·¡è§Ĩ
    -0.23
    å·¡
    -0.22
     ngh
    -0.22
    POSITIVE LOGITS
     homogeneous
    0.26
    utable
    0.26
     Majority
    0.25
    并éĢļè¿ĩ
    0.25
    ä¸ĢæŃ¥æŃ¥
    0.24
     Housing
    0.24
     mostly
    0.24
     Ley
    0.23
    edList
    0.23
     Tod
    0.23
    Activations Density 0.023%

    No Known Activations