© 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. 33-TRANSCODER-HP
    7. 53412
    Prev
    Next
    INDEX
    Explanations

    feces/poop

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nbsp
    -0.27
    便
    -0.27
    漫çĶ»
    -0.26
     mast
    -0.25
    .ua
    -0.25
    inherits
    -0.25
    æĺ¯éĿŀ
    -0.25
     Sle
    -0.24
     vign
    -0.24
    æļ´
    -0.24
    POSITIVE LOGITS
    fram
    0.34
    manent
    0.29
    ci
    0.29
    ä»Ģ
    0.28
     dro
    0.28
    áln
    0.27
    è·ij
    0.27
     fir
    0.27
     fle
    0.26
    iod
    0.26
    Activations Density 0.017%

    No Known Activations