© 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. 107909
    Prev
    Next
    INDEX
    Explanations

    code and computing

    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
    åIJĪæł¼
    -0.28
    çģ°
    -0.28
    礼
    -0.26
    å¿Ĺ
    -0.26
    ä¿¡
    -0.26
     bli
    -0.25
    Quality
    -0.25
    éĻIJ
    -0.25
    suit
    -0.25
    gra
    -0.24
    POSITIVE LOGITS
    èĩªçĦ¶èĢĮ
    0.32
    илÑĮно
    0.31
    é¾ĻéŨ
    0.29
    emachine
    0.25
    å¾Ĥ
    0.25
     Ñĩа
    0.24
     vÃłng
    0.24
    æł²
    0.24
    ç¢Ľ
    0.24
    izar
    0.23
    Activations Density 1.702%

    No Known Activations