© 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. 130739
    Prev
    Next
    INDEX
    Explanations

    royalty

    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
    caret
    -0.29
    åı¯èĥ½åŃĺåľ¨
    -0.27
    assistant
    -0.25
    çĮĹ
    -0.25
    æī¿æĭħ
    -0.25
    appa
    -0.25
    _KIND
    -0.25
    çºł
    -0.25
    èĿī
    -0.24
    åľ°æĸ¹æĶ¿åºľ
    -0.24
    POSITIVE LOGITS
    ,"\
    0.28
    arsity
    0.27
    æŀŀ
    0.27
    åĻ¨æĿIJ
    0.26
    'aff
    0.26
    .which
    0.25
    -pill
    0.25
    ',"
    0.25
     variable
    0.25
    bern
    0.25
    Activations Density 11.857%

    No Known Activations