© 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. 30-TRANSCODER-HP
    7. 95971
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vol
    -0.27
     wol
    -0.27
    vos
    -0.26
     concentration
    -0.25
     demand
    -0.25
    /msg
    -0.25
    ola
    -0.25
    -sem
    -0.24
    {}\
    -0.24
     sut
    -0.24
    POSITIVE LOGITS
    orian
    0.29
    å°±è¶Ĭ
    0.28
    ories
    0.27
    æĽ´å¤ļ
    0.27
    ابة
    0.26
     Cincinnati
    0.25
    è·¯è¿ĩ
    0.25
    ç«ĭ
    0.25
    æĽ´å¤ļçļĦ
    0.25
    Enumeration
    0.25
    Activations Density 0.121%

    No Known Activations