© 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. 142074
    Prev
    Next
    INDEX
    Explanations

    comparisons

    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
     Slice
    -0.27
    uela
    -0.27
    å¸ĸåŃIJ
    -0.26
     Treaty
    -0.24
    )")↵↵
    -0.24
     Scho
    -0.24
     конкÑĥÑĢÑģ
    -0.24
    åı«æĪij
    -0.24
    alytics
    -0.23
    astically
    -0.23
    POSITIVE LOGITS
    ecast
    0.29
    cycl
    0.28
    legg
    0.27
    iger
    0.27
    ä¹ĭç±»
    0.27
    zl
    0.27
    esp
    0.26
    pur
    0.26
    cid
    0.26
     mount
    0.25
    Activations Density 26.084%

    No Known Activations