© 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. 53325
    Prev
    Next
    INDEX
    Explanations

    M or

    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
     Dra
    -0.27
    esi
    -0.27
    ifu
    -0.26
    eki
    -0.26
    eka
    -0.24
     дела
    -0.24
    è¿Ń
    -0.24
    ocale
    -0.24
    bel
    -0.24
     ocas
    -0.24
    POSITIVE LOGITS
    kest
    0.27
    æļij
    0.25
    xygen
    0.25
    alte
    0.25
    欧å¼ı
    0.25
    åİŁæĿ¥æĺ¯
    0.24
    èħĶ
    0.24
    åIJĦè¡Į
    0.24
    绣ä¸Ģ
    0.24
    ç¢ī
    0.24
    Activations Density 0.021%

    No Known Activations