© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7319
    Prev
    Next
    INDEX
    Explanations

    regulation

    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
    ild
    -0.28
    /goto
    -0.27
     diret
    -0.26
    ENARIO
    -0.26
    èµĸ以
    -0.26
    оÑĤов
    -0.25
    abouts
    -0.25
    -collapse
    -0.24
    ouce
    -0.24
    ç¢İçīĩ
    -0.23
    POSITIVE LOGITS
     Comp
    0.26
     snow
    0.25
     technically
    0.24
     od
    0.24
    ä½Ĩå®ĥ
    0.24
    IT
    0.24
    绣ä¸Ģ
    0.24
    <=$
    0.24
    tokenId
    0.24
    Pull
    0.24
    Activations Density 0.039%

    No Known Activations