© 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. 129843
    Prev
    Next
    INDEX
    Explanations

    saying, believing

    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
    ollapse
    -0.27
    ircular
    -0.25
    æİ¢
    -0.25
    è¿Ļ个è¯į
    -0.24
     Explosion
    -0.24
    奶
    -0.24
    åĽļ
    -0.24
    locked
    -0.24
    稿
    -0.24
    没åħ³ç³»
    -0.24
    POSITIVE LOGITS
    itives
    0.27
    ?key
    0.27
    enschaft
    0.27
    Ñĥв
    0.26
     Hunts
    0.26
    iÃŁ
    0.26
    (include
    0.25
     Venez
    0.25
    ×Ļ×ł×ª
    0.24
    /goto
    0.24
    Activations Density 12.013%

    No Known Activations