© 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. 88788
    Prev
    Next
    INDEX
    Explanations

    1

    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
    ouser
    -0.25
    æ¥ŀ
    -0.25
    ry
    -0.24
     Honour
    -0.24
    ulta
    -0.23
    -being
    -0.23
     instant
    -0.23
    oday
    -0.23
    åľ¨ä¹İ
    -0.23
    alach
    -0.23
    POSITIVE LOGITS
    她们
    0.28
    urable
    0.27
    &utm
    0.25
    åIJĮåŁİ
    0.25
    auté
    0.24
    çħŀ
    0.24
    .scala
    0.24
    _actual
    0.24
    danger
    0.24
    uity
    0.24
    Activations Density 4.343%

    No Known Activations