© 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. 8751
    Prev
    Next
    INDEX
    Explanations

    programming

    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
     sam
    -0.33
     Balls
    -0.27
    ete
    -0.27
    ionate
    -0.27
    åĪ«
    -0.27
    oted
    -0.27
    oting
    -0.27
    ington
    -0.27
     det
    -0.27
    isnan
    -0.26
    POSITIVE LOGITS
    lation
    0.26
    ä¸ĩåħ¬éĩĮ
    0.25
    izzo
    0.25
     ksiÄħż
    0.25
    ç»´å°Ķ
    0.25
     initData
    0.25
    ortho
    0.24
     McCl
    0.24
     minLength
    0.24
     triggering
    0.24
    Activations Density 0.111%

    No Known Activations