© 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. 31-TRANSCODER-HP
    7. 19451
    Prev
    Next
    INDEX
    Explanations

    technical descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    溯
    -0.26
    ienes
    -0.26
    çĦī
    -0.26
    irting
    -0.26
    ä¸ĢæĿ¡
    -0.26
     strategically
    -0.25
    cast
    -0.25
    polit
    -0.25
     urgently
    -0.24
    èĭ±æīį
    -0.24
    POSITIVE LOGITS
    obe
    0.29
    obel
    0.26
    éĥ½ä¸įèĥ½
    0.25
    asse
    0.25
     réfé
    0.24
    ä¸Ģæł·çļĦ
    0.24
     apart
    0.24
    prepend
    0.24
    ç§ij
    0.24
    ZERO
    0.24
    Activations Density 0.001%

    No Known Activations