© 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. 42019
    Prev
    Next
    INDEX
    Explanations

    other

    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
    that
    -0.31
    	that
    -0.30
    That
    -0.28
    å¿Ĺ强
    -0.28
    _that
    -0.27
     THAT
    -0.26
    aka
    -0.26
    éĤ£å°±æĺ¯
    -0.26
     that
    -0.25
     That
    -0.25
    POSITIVE LOGITS
     other
    0.87
    åħ¶ä»ĸ
    0.80
    åħ¶å®ĥ
    0.70
    other
    0.68
     otras
    0.63
     altre
    0.63
     Other
    0.63
    åħ¶ä»ĸçļĦ
    0.62
    _other
    0.62
    Other
    0.61
    Activations Density 0.000%

    No Known Activations