© 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. 20-TRANSCODER-HP
    7. 107728
    Prev
    Next
    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åįļ
    -0.26
    ç«ĭãģ¦
    -0.25
    Together
    -0.25
     together
    -0.24
    é£Ł
    -0.24
    егод
    -0.23
    è¾Ĺ
    -0.23
    åĿij
    -0.23
    OrDefault
    -0.23
    èĩªçĦ¶èĢĮ
    -0.23
    POSITIVE LOGITS
    mentions
    0.28
    æ¦Ĥ念
    0.27
    -rise
    0.27
     prerequisite
    0.26
    EIF
    0.25
     skeptic
    0.25
    åģı
    0.24
    aden
    0.24
     Pearce
    0.24
     unt
    0.24
    Activations Density 11.762%

    No Known Activations