© 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. 53667
    Prev
    Next
    INDEX
    Explanations

    fairy tales and fantasy

    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
    è´¨
    -0.28
     Tet
    -0.28
    ocache
    -0.25
    uet
    -0.25
    éĥ½æĥ³
    -0.24
    (Function
    -0.24
     tet
    -0.24
    ORN
    -0.23
     ted
    -0.23
    Affected
    -0.23
    POSITIVE LOGITS
     Gro
    0.26
    .Flags
    0.26
    ä¸īæĺ¯
    0.26
    Flo
    0.25
    ä¸Ģ群人
    0.25
     quần
    0.25
    .pipe
    0.24
    æĢ»éĺŁ
    0.24
    Gro
    0.24
    angler
    0.24
    Activations Density 0.008%

    No Known Activations