© 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. 107609
    Prev
    Next
    INDEX
    Explanations

    Coach

    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
     Shaft
    -0.30
    yme
    -0.27
    è¿ĽæĿ¥
    -0.27
    wash
    -0.25
    æī¹
    -0.25
    ede
    -0.25
    æijĩ
    -0.24
    ä¸Ģåıªæīĭ
    -0.24
    emark
    -0.24
     shaft
    -0.24
    POSITIVE LOGITS
    Ctl
    0.29
    umbo
    0.28
     advis
    0.25
    åıijæĺİä¸ĵåĪ©
    0.25
    ,',
    0.24
    ]**
    0.24
    OST
    0.24
    ">*</
    0.23
    ENGINE
    0.23
    ặt
    0.23
    Activations Density 11.903%

    No Known Activations