© 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. 25-TRANSCODER-HP
    7. 108123
    Prev
    Next
    INDEX
    Explanations

    for

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĵį
    -0.26
    æĥ©ç½ļ
    -0.26
    æĪIJå°±
    -0.25
     quis
    -0.25
    è¿ĩç¨ĭå½ĵä¸Ń
    -0.24
    è¾¾æłĩ
    -0.24
    oter
    -0.24
    æĥ³
    -0.24
    positions
    -0.23
    /lg
    -0.23
    POSITIVE LOGITS
     i
    0.35
     ii
    0.31
    lined
    0.30
     spl
    0.29
     x
    0.28
    çĽı
    0.27
     interior
    0.26
    phan
    0.25
    æŃĨ
    0.25
     rou
    0.25
    Activations Density 1.020%

    No Known Activations