© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 32-TRANSCODER-HP
    7. 44195
    Prev
    Next
    INDEX
    Explanations

    Code/share links

    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
    Negative Logits
    æĿĥçĽĬ
    -0.26
    Ns
    -0.25
    sse
    -0.25
    éĢģæĿ¥
    -0.25
    èįī
    -0.25
     ND
    -0.25
    åĽ½èµĦå§Ķ
    -0.25
     ingen
    -0.24
    å½Ŀ
    -0.24
    _prefs
    -0.24
    POSITIVE LOGITS
     Stack
    0.27
    ä¸ĢåĿĹ
    0.27
     bat
    0.27
    ctica
    0.27
    Stack
    0.26
    acob
    0.26
    bad
    0.25
     parent
    0.25
    cheon
    0.24
    -chain
    0.24
    Activations Density 0.000%

    No Known Activations