© 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. 130121
    Prev
    Next
    INDEX
    Explanations

    Parentheses

    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
    unj
    -0.32
    reur
    -0.28
    uer
    -0.25
    atori
    -0.25
    linger
    -0.25
    iju
    -0.24
    ordinator
    -0.24
    Ã¼ÃŁ
    -0.23
     Rox
    -0.23
    atus
    -0.23
    POSITIVE LOGITS
    æ¡ĪåŃIJ
    0.31
    åºŃ审
    0.29
    éĹ®é¢ĺæĺ¯
    0.29
    æī¿æĭħ责任
    0.28
    ibur
    0.28
    绾
    0.25
    AuthService
    0.25
    åı£å¤´
    0.24
    çĿģ
    0.23
    ivec
    0.23
    Activations Density 7.736%

    No Known Activations