© 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. 20-TRANSCODER-HP
    7. 142219
    Prev
    Next
    INDEX
    Explanations

    A

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ESIS
    -0.27
    æĪij以为
    -0.25
    家å±ŀ
    -0.25
    ä½ľä¸ºä¸Ģ个
    -0.25
    ç§Ģ
    -0.24
    Èĭ
    -0.24
    éģ¿å¼Ģ
    -0.24
    urm
    -0.24
    æĤī
    -0.23
    å®īæİĴ
    -0.23
    POSITIVE LOGITS
    ilename
    0.28
    izzly
    0.26
     alternative
    0.26
     Slug
    0.26
    lore
    0.25
    riter
    0.24
    mitt
    0.24
    ylene
    0.24
    \\"
    0.24
    ceptions
    0.24
    Activations Density 30.007%

    No Known Activations