© 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. 53352
    Prev
    Next
    INDEX
    Explanations

    code, licenses, documentation

    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
    elm
    -0.30
    -eng
    -0.24
    repid
    -0.24
    ï½ŀ↵↵
    -0.24
    caps
    -0.24
     tant
    -0.24
    .cljs
    -0.23
    _least
    -0.23
    vy
    -0.23
    orst
    -0.23
    POSITIVE LOGITS
    contin
    0.27
    éĴŀ
    0.25
    è§Ħç¨ĭ
    0.25
    æĿ³
    0.24
     underground
    0.24
    ãĥį
    0.24
     diver
    0.23
    å¹²é¢Ħ
    0.23
     подпиÑģ
    0.23
    ASS
    0.23
    Activations Density 0.003%

    No Known Activations