© 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. 53292
    Prev
    Next
    INDEX
    Explanations

    be

    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
     dist
    -0.34
    æĻº
    -0.30
     RELATED
    -0.30
    éĢļ
    -0.29
    	dist
    -0.26
     Shooting
    -0.26
    æĸ¹éĿ¢çļĦ
    -0.25
    æĻºèĥ½åĮĸ
    -0.25
    _DIST
    -0.25
    dist
    -0.25
    POSITIVE LOGITS
     hand
    0.31
    terdam
    0.29
     light
    0.29
    éĺ³
    0.28
    -double
    0.27
    ä¸įé«ĺ
    0.26
     concerned
    0.26
    ANTI
    0.26
    TS
    0.25
     square
    0.25
    Activations Density 0.015%

    No Known Activations