© 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. 87387
    Prev
    Next
    INDEX
    Explanations

    Articles

    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
    åīįæıIJæĺ¯
    -0.29
    ATOM
    -0.27
    ä¿£
    -0.27
    åı¦å¤ĸä¸Ģ个
    -0.27
    ilded
    -0.26
    MainActivity
    -0.26
    rü
    -0.25
    æĪĸå¤ļ
    -0.25
    çļĦåīįæıIJ
    -0.25
    __$
    -0.24
    POSITIVE LOGITS
    åģĩæĹ¥
    0.25
    å·®å¼ĤåĮĸ
    0.25
     Burl
    0.25
     japanese
    0.24
     hall
    0.24
    rical
    0.23
    chest
    0.23
    ooled
    0.23
    åĽŀå½Ĵ
    0.23
     euler
    0.23
    Activations Density 0.009%

    No Known Activations