© 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. 88551
    Prev
    Next
    INDEX
    Explanations

    code and technical writing

    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
     Apply
    -0.29
    èµı
    -0.28
     applies
    -0.28
    gü
    -0.28
    imp
    -0.28
    åĽ´
    -0.28
     apply
    -0.28
    è³ŀ
    -0.26
    iled
    -0.25
     Imp
    -0.25
    POSITIVE LOGITS
    rics
    0.29
    ãģ¡ãģ¯
    0.27
    icorn
    0.26
    Lik
    0.25
    æī¹åıijå¸Ĥåľº
    0.25
    訾
    0.25
     conveniently
    0.24
    å¤ĩçĶ¨
    0.24
    ique
    0.24
    åįłåľ°éĿ¢ç§¯
    0.24
    Activations Density 66.178%

    No Known Activations