© 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. 22-TRANSCODER-HP
    7. 88195
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #ad
    -0.28
    pagination
    -0.27
     sal
    -0.24
    åı¯æĥľ
    -0.24
    \S
    -0.24
    <dd
    -0.24
    æµ·æ°´
    -0.24
    icot
    -0.24
     centre
    -0.24
    å¿ĺè®°äºĨ
    -0.24
    POSITIVE LOGITS
     WH
    0.32
    æĪijä»¬çŁ¥éģĵ
    0.30
     Manson
    0.28
    åij¨è½¬
    0.26
    WH
    0.26
    ä¼ģä¸ļæıIJä¾Ľ
    0.25
    è¿Ļ个è¯į
    0.25
    Backing
    0.24
    éĹ®é¢ĺæĺ¯
    0.24
    entially
    0.24
    Activations Density 0.004%

    No Known Activations