© 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. 108600
    Prev
    Next
    INDEX
    Explanations

    search

    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
    åĮĸåIJĪçī©
    -0.29
    让æ¶Īè´¹èĢħ
    -0.29
     Establishment
    -0.27
    让æĤ¨
    -0.27
    请èģĶç³»
    -0.27
    让çĶ¨æĪ·
    -0.27
    让大家
    -0.26
    PLOY
    -0.26
    çĭ¬ä¸Ģ
    -0.25
    è¿ĶåĽŀæIJľçĭIJ
    -0.25
    POSITIVE LOGITS
     Google
    0.34
     peek
    0.29
     inc
    0.28
     idea
    0.26
     Inc
    0.26
     back
    0.26
    Google
    0.26
    inc
    0.25
     "...
    0.25
     toned
    0.24
    Activations Density 0.946%

    No Known Activations