© 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. 40023
    Prev
    Next
    INDEX
    Explanations

    code and math related texts

    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
    éĴķ
    -0.29
    orge
    -0.27
     Euler
    -0.26
     grandfather
    -0.26
     slap
    -0.26
    èµ·éĩįæľº
    -0.25
    çĶŁäº§æĢ»åĢ¼
    -0.25
     PROGMEM
    -0.25
    èĩŃ
    -0.24
    uglify
    -0.24
    POSITIVE LOGITS
    isi
    0.40
    etto
    0.36
    iso
    0.35
    isy
    0.33
    mo
    0.33
    ible
    0.32
    ivi
    0.31
    ippo
    0.31
    i
    0.31
    iate
    0.31
    Activations Density 2.799%

    No Known Activations