© 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. 42451
    Prev
    Next
    INDEX
    Explanations

    breathing

    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
    odb
    -0.31
     deep
    -0.29
    Deep
    -0.27
    uste
    -0.27
    deep
    -0.26
    PROP
    -0.26
     PROP
    -0.26
    æĻ®éģįåŃĺåľ¨
    -0.25
    _deep
    -0.24
     Deep
    -0.24
    POSITIVE LOGITS
    while
    0.30
     vá
    0.27
     endwhile
    0.27
     while
    0.27
    å¾Ĺå¾Ī
    0.27
    第ä¸Ģéĥ¨
    0.27
    	while
    0.26
     granularity
    0.26
     whilst
    0.26
    èĢĮ
    0.25
    Activations Density 0.001%

    No Known Activations