© 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. 107961
    Prev
    Next
    INDEX
    Explanations

    Reasons/cause

    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
    è¿ĶåĽŀæIJľçĭIJ
    -0.29
    ãĤªãĤ¹ãĤ¹ãĥ¡
    -0.28
    èĢĮå·²
    -0.27
    rix
    -0.27
    @email
    -0.26
    æľīæĽ´å¥½çļĦ
    -0.26
    åı¸é©¬
    -0.26
    	best
    -0.26
    éĻ¤æѤ
    -0.25
    arness
    -0.25
    POSITIVE LOGITS
    é¡¹çĽ®çļĦ
    0.28
    throp
    0.28
    hom
    0.25
    akh
    0.24
     Joh
    0.24
     act
    0.24
     actu
    0.23
    ав
    0.23
     d
    0.23
    arty
    0.23
    Activations Density 31.366%

    No Known Activations