© 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. 107306
    Prev
    Next
    INDEX
    Explanations

    orphism

    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
    thy
    -0.29
    PG
    -0.27
    ãģ©ãĤĵãģ©ãĤĵ
    -0.27
    cretion
    -0.26
    _PG
    -0.26
    æĥłæ°ij
    -0.25
     Rolling
    -0.25
     pg
    -0.24
    MC
    -0.24
     PG
    -0.24
    POSITIVE LOGITS
    主è¦ģæĺ¯
    0.40
    æĺ¯åĽłä¸º
    0.39
    çļĦåİŁåĽł
    0.36
    è¿Ļæĺ¯åĽłä¸º
    0.35
    æĺ¯å¯¹
    0.35
    说çļĦæĺ¯
    0.35
    æĿ¥èĩªäºİ
    0.32
    çļĦç¼ĺ
    0.31
    æºIJäºİ
    0.31
    主è¦ģçĶ¨äºİ
    0.31
    Activations Density 41.467%

    No Known Activations