© 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. 108173
    Prev
    Next
    INDEX
    Explanations

    Mixed online content excerpts

    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
    terior
    -0.30
    çī¹ä»·
    -0.28
    æµ´
    -0.27
    çīº
    -0.27
    UILayout
    -0.27
    çĪ¶åŃIJ
    -0.26
    illing
    -0.25
    åĩĨå¤ĩå·¥ä½ľ
    -0.25
    è´¨éĩıåĴĮ
    -0.25
     trụ
    -0.25
    POSITIVE LOGITS
    odef
    0.30
    åĪĨå¸ĥ
    0.28
    eper
    0.27
    輪
    0.27
    iros
    0.27
    Parsed
    0.26
    éģıåĪ¶
    0.24
     GOOD
    0.24
    .asp
    0.24
    Picker
    0.24
    Activations Density 7.491%

    No Known Activations