© 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. 64274
    Prev
    Next
    INDEX
    Explanations

    review

    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
    .nr
    -0.33
    olen
    -0.28
    дол
    -0.26
    ·¨
    -0.26
     taller
    -0.25
    -Pacific
    -0.25
    æĹ¥æŃ£å¼ı
    -0.24
    ceptors
    -0.24
     stap
    -0.23
    èĹIJ
    -0.23
    POSITIVE LOGITS
    åı¶
    0.29
    ToOne
    0.28
    导èĩ´
    0.27
    æĻĭ
    0.26
     URLSession
    0.25
     instant
    0.24
    licit
    0.24
    åı¶çīĩ
    0.24
    æĹ©
    0.24
    åħĪè¡Į
    0.23
    Activations Density 0.052%

    No Known Activations