© 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. 108422
    Prev
    Next
    INDEX
    Explanations

    a/an

    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
    åıĤ
    -0.28
    æĹ¢çĦ¶
    -0.27
     starving
    -0.27
     drove
    -0.26
    -saving
    -0.26
    æĺŁéĻħ
    -0.25
    åIJ¯
    -0.25
    yte
    -0.25
    éļ¾æĢª
    -0.25
    纷纷
    -0.25
    POSITIVE LOGITS
    lander
    0.27
    ка
    0.26
     Schedule
    0.24
     issues
    0.24
    issues
    0.24
    à¸İ
    0.23
    ellen
    0.23
    ä¸ĬæĿ¥
    0.23
    лем
    0.23
     schedule
    0.23
    Activations Density 0.916%

    No Known Activations