© 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. 19061
    Prev
    Next
    INDEX
    Explanations

    the or a

    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
    ä¸Ń级
    -0.28
    -scrollbar
    -0.26
    设计å¸Ī
    -0.24
    ior
    -0.24
    onds
    -0.24
    kers
    -0.24
    ypes
    -0.24
    körper
    -0.24
     destruct
    -0.24
    adder
    -0.24
    POSITIVE LOGITS
    è¿IJ
    0.30
    客
    0.29
    plain
    0.28
    SPAN
    0.28
     mat
    0.28
    lap
    0.28
     MAT
    0.27
    ucid
    0.27
     Tek
    0.27
    游
    0.26
    Activations Density 1.093%

    No Known Activations