© 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. 35-TRANSCODER-HP
    7. 39133
    Prev
    Next
    INDEX
    Explanations

    code/technical documentation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĤ¬å´ĸ
    -0.28
     manifestations
    -0.26
    ä¸įä»ħè¦ģ
    -0.25
     ÑĩÑĥвÑģÑĤво
    -0.25
    æľĽçĿĢ
    -0.24
     Äijảm
    -0.24
    è¿Ļæł·åģļ
    -0.24
    æĬĬæı¡
    -0.24
    æĬĵ
    -0.23
     PURPOSE
    -0.23
    POSITIVE LOGITS
    ott
    0.32
    itten
    0.32
    ror
    0.30
    rete
    0.30
    ther
    0.30
    atos
    0.29
    oss
    0.29
    rr
    0.28
    aker
    0.28
    uten
    0.28
    Activations Density 11.912%

    No Known Activations