© 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. 54118
    Prev
    Next
    INDEX
    Explanations

    computer instructions

    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
    ç£IJ
    -0.30
    arily
    -0.30
    pond
    -0.27
    ç«ĭ
    -0.25
    ãĥ«ãĥī
    -0.24
    èĤ¯
    -0.24
     stacked
    -0.24
    åħ¬
    -0.23
    icom
    -0.23
    .Web
    -0.23
    POSITIVE LOGITS
    mur
    0.28
    -sc
    0.25
    æľįåĬ¡æ°´å¹³
    0.25
    æĺ¯æĪijåĽ½
    0.24
    zar
    0.24
    udio
    0.23
    rtl
    0.23
    aws
    0.23
    çĮ«
    0.23
    -zero
    0.23
    Activations Density 0.020%

    No Known Activations