© 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. 107494
    Prev
    Next
    INDEX
    Explanations

    scientific abstracts

    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
    eron
    -0.31
     Engl
    -0.25
     NOTICE
    -0.25
    æĹłæĦı
    -0.24
     Hour
    -0.24
     arrive
    -0.24
    ahir
    -0.24
    éĶķ
    -0.24
    lobal
    -0.24
     overt
    -0.23
    POSITIVE LOGITS
    ingerprint
    0.26
    å¾ĴæŃ¥
    0.25
     quali
    0.25
     Seed
    0.25
    Seed
    0.25
    ä¸Ģè·¯
    0.25
    seed
    0.25
     seed
    0.25
    æİĪ
    0.24
     RW
    0.24
    Activations Density 4.241%

    No Known Activations