© 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. 18-TRANSCODER-HP
    7. 89741
    Prev
    Next
    INDEX
    Explanations

    Braces and/or brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æİĴ
    -0.28
    umann
    -0.27
    两æĿ¡
    -0.27
    æĹ·
    -0.27
    çĺģ
    -0.26
    åĪ¶åĵģ
    -0.26
     fin
    -0.26
     especÃŃfica
    -0.26
     fines
    -0.25
    æľ«
    -0.25
    POSITIVE LOGITS
     meters
    0.29
    ISK
    0.27
    ayed
    0.25
    UCK
    0.25
    IEW
    0.24
    ç©¿éĢı
    0.24
    lest
    0.24
    astle
    0.24
    çªģçł´
    0.24
    foods
    0.23
    Activations Density 8.516%

    No Known Activations