© 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. 108177
    Prev
    Next
    INDEX
    Explanations

    with

    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
    ä¼´éļı
    -0.32
    åĨĻä¸ĭ
    -0.30
    Associated
    -0.28
    对åºĶçļĦ
    -0.27
    apixel
    -0.26
     accompanying
    -0.25
    沿éĢĶ
    -0.24
    èĻļ
    -0.24
    Å¡ÃŃ
    -0.24
    èĥ¯
    -0.24
    POSITIVE LOGITS
     mi
    0.28
    è¿Ļæīįæĺ¯
    0.27
    irse
    0.27
     bunch
    0.25
     sold
    0.25
    åĶ®ä»·
    0.24
    itti
    0.24
    人士
    0.24
    åİŁæĿ¥æĺ¯
    0.24
     fo
    0.23
    Activations Density 0.134%

    No Known Activations