© 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. 142371
    Prev
    Next
    INDEX
    Explanations

    Foreign languages/characters

    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
    uft
    -0.29
    ç
    -0.28
    åĨĻåĩº
    -0.28
    讲
    -0.27
    -learning
    -0.27
    æ³Ľ
    -0.27
    æµ·
    -0.27
    æ£Ģæµĭ
    -0.26
    -wide
    -0.26
     convince
    -0.26
    POSITIVE LOGITS
    åħ¬æĬ¥
    0.25
    å±ģèĤ¡
    0.25
     UsersController
    0.24
    åĦĨ
    0.24
     ActiveSupport
    0.24
    _wire
    0.24
    oky
    0.24
    ìĭ±
    0.24
     Daily
    0.24
    VML
    0.23
    Activations Density 5.878%

    No Known Activations