© 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. 39245
    Prev
    Next
    INDEX
    Explanations

    Scre

    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
    eel
    -0.27
    owel
    -0.27
    som
    -0.27
    èݼ
    -0.26
    æ¾į
    -0.26
     backlash
    -0.26
    ä¸Ģå®ļ
    -0.25
    åľ°éģĵ
    -0.25
    éķľ
    -0.25
    adel
    -0.25
    POSITIVE LOGITS
    ec
    0.26
    åĽ¾ä¸º
    0.26
     Nations
    0.24
    ific
    0.24
     дог
    0.23
     Fre
    0.23
     equivalents
    0.23
    ump
    0.23
    客æĪ·æıIJä¾Ľ
    0.23
    elts
    0.23
    Activations Density 76.452%

    No Known Activations