© 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. 63816
    Prev
    Next
    INDEX
    Explanations

    period

    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
    æ´Ļ
    -0.29
    éŀij
    -0.26
    æ±²
    -0.25
    çļĦèĦ¸
    -0.25
     PAD
    -0.25
     COMMENT
    -0.24
    转æį¢
    -0.24
    trap
    -0.23
     nast
    -0.23
    转åıĺ
    -0.23
    POSITIVE LOGITS
     Barcl
    0.27
    Ħ件
    0.24
    ìĹ°
    0.24
    èIJİ缩
    0.24
     arc
    0.24
    cri
    0.23
     Boyd
    0.23
    ellery
    0.23
     Plain
    0.23
    çī¹åĪ«æĺ¯
    0.23
    Activations Density 50.447%

    No Known Activations