© 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. 63685
    Prev
    Next
    INDEX
    Explanations

    unformatted text snippets

    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
    tees
    -0.32
    å¹³åİŁ
    -0.28
    Inspectable
    -0.26
    rente
    -0.26
    Datetime
    -0.25
    rees
    -0.24
    侵害
    -0.24
    atory
    -0.24
    riors
    -0.23
    Toe
    -0.23
    POSITIVE LOGITS
     Spo
    0.30
    ä¹ĭä¸Ģ
    0.28
    æīĢåľ¨
    0.26
    éĢı
    0.26
    è´¥
    0.26
    åħ¶ä¸Ńä¹ĭä¸Ģ
    0.26
    æĸ¹éĿ¢
    0.25
    estr
    0.25
    åħ¶ä¸Ńä¸Ģ个
    0.25
    chg
    0.24
    Activations Density 62.409%

    No Known Activations