© 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. 32-TRANSCODER-HP
    7. 43425
    Prev
    Next
    INDEX
    Explanations

    Removing or changing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èĩªå¸¦
    -0.28
     headlights
    -0.25
     pools
    -0.25
     Own
    -0.25
    -tags
    -0.25
     pool
    -0.24
    éĿ¢ä¸Ĭ
    -0.24
    -vous
    -0.24
    èĥĥ
    -0.24
    rats
    -0.23
    POSITIVE LOGITS
     collapsed
    0.30
    collapsed
    0.30
     missed
    0.30
     interpolated
    0.29
     omitted
    0.29
     ab
    0.29
     erased
    0.29
    anted
    0.28
     eliminated
    0.28
     departed
    0.28
    Activations Density 0.002%

    No Known Activations