© 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. 88727
    Prev
    Next
    INDEX
    Explanations

    to

    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
    aldi
    -0.29
    娣
    -0.28
    andi
    -0.27
    è¦ģåģļ
    -0.27
    kip
    -0.26
    åģļå·¥
    -0.26
    å¾ĪæŃ£å¸¸
    -0.25
    zig
    -0.25
    æ¯Ķäºļ
    -0.25
     moden
    -0.25
    POSITIVE LOGITS
     heads
    0.25
    æĺ¯æĢİæł·
    0.25
    jar
    0.24
    /head
    0.23
     SPDX
    0.23
     adherence
    0.23
    骥
    0.23
     head
    0.23
    iddles
    0.22
    æĺ¯å¦Ĥä½ķ
    0.22
    Activations Density 16.386%

    No Known Activations