© 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. 107520
    Prev
    Next
    INDEX
    Explanations

    hyster

    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
    åģļ梦
    -0.30
    pository
    -0.27
    nika
    -0.27
    亥
    -0.27
    anon
    -0.26
     hol
    -0.26
    èIJ½åı¶
    -0.25
    sı
    -0.25
    ç§ģèIJ¥
    -0.25
    主æĮģåı¬å¼Ģ
    -0.24
    POSITIVE LOGITS
     compart
    0.25
    IT
    0.25
    Church
    0.24
    ä¸įè¿ĩ
    0.24
    ]=[
    0.23
     wipes
    0.23
    åĨ·
    0.23
    æ´Ĺ
    0.23
    游
    0.23
    寧
    0.23
    Activations Density 0.908%

    No Known Activations