© 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. 108279
    Prev
    Next
    INDEX
    Explanations

    Code, licenses, papers

    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
    åĪļå¼Ģå§ĭ
    -0.29
    å°¤
    -0.26
    sylvania
    -0.26
    ãģĺ
    -0.26
    ä¼ļ议精ç¥ŀ
    -0.25
    èijĨ
    -0.25
    交ä¼ļ
    -0.25
    antan
    -0.25
    ATIONS
    -0.25
    åľ¨è¿Ļ个
    -0.24
    POSITIVE LOGITS
     perfect
    0.26
    lé
    0.26
    llib
    0.25
     perfectly
    0.25
     Grinder
    0.25
     Hire
    0.24
    顺
    0.24
    åħ¨å¤©
    0.24
    .pretty
    0.24
    åıĪèĥ½
    0.23
    Activations Density 0.125%

    No Known Activations