© 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. 40021
    Prev
    Next
    INDEX
    Explanations

    non

    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
    esi
    -0.30
    tÃŃ
    -0.29
    R
    -0.28
    ija
    -0.28
    P
    -0.28
    ajÄħ
    -0.28
    ت
    -0.28
    ência
    -0.27
    ui
    -0.27
    Ŀ
    -0.27
    POSITIVE LOGITS
    æīĵåħ¥
    0.28
    åģļ强
    0.27
    代åĬŀ
    0.26
     inadvert
    0.26
     exem
    0.25
    æĴĩ
    0.25
    èĢĥä¸Ĭ
    0.25
     barric
    0.25
     underage
    0.25
    被åĪ¤
    0.25
    Activations Density 0.837%

    No Known Activations