© 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. 7986
    Prev
    Next
    INDEX
    Explanations

    Sentence structure and code

    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
     usÅĤug
    -0.26
    -plugins
    -0.26
    èĬ±éĴ±
    -0.25
    -risk
    -0.25
    å·´å·´
    -0.25
    mime
    -0.24
    Grow
    -0.24
    _invoke
    -0.24
    rne
    -0.24
    primitive
    -0.24
    POSITIVE LOGITS
    详ç»ĨçļĦ
    0.28
    lee
    0.27
    åĭĺ
    0.27
    WT
    0.26
     twink
    0.26
     ella
    0.25
    æķ´ä¸ª
    0.24
    转
    0.24
     cred
    0.24
    eor
    0.24
    Activations Density 0.012%

    No Known Activations