© 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. 89387
    Prev
    Next
    INDEX
    Explanations

    average

    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
    ök
    -0.29
    缴æİ¥
    -0.29
    ude
    -0.28
    æļ´éĽ¨
    -0.27
    ANDING
    -0.27
    è¡Įç¨ĭ
    -0.26
    çĽ´è¾¾
    -0.26
     Overflow
    -0.25
     türlü
    -0.25
    ince
    -0.25
    POSITIVE LOGITS
    è¿Ļåıª
    0.29
    âŀķ
    0.27
     competitiveness
    0.27
    =w
    0.26
     Whites
    0.26
     competition
    0.26
    lopen
    0.25
    åĮºå§Ķ
    0.25
    åŃº
    0.25
    å¸Ĥåľºç«ŀäºī
    0.24
    Activations Density 4.402%

    No Known Activations