© 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. 9064
    Prev
    Next
    INDEX
    Explanations

    Wikipedia articles

    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
    è´§å¸ģ
    -0.25
    tha
    -0.25
    æ²»å®ī
    -0.25
    itarian
    -0.24
    ç»į
    -0.24
    ç¾Ķ
    -0.23
    ingu
    -0.23
    UPPORTED
    -0.23
     khu
    -0.23
    eder
    -0.23
    POSITIVE LOGITS
    %M
    0.27
    'L
    0.26
    "—
    0.25
    å¼ĢäºĨ
    0.25
    @g
    0.25
     disposing
    0.24
    å®ŀåľ¨
    0.24
     Kron
    0.24
    %i
    0.24
    --,
    0.24
    Activations Density 0.017%

    No Known Activations