© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 4-TRANSCODER-HP
    7. 243
    Prev
    Next
    INDEX
    Explanations

    arena

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    acker
    -0.30
    .yahoo
    -0.26
    åħ¥åĽŃ
    -0.26
    å¼Ģåĩº
    -0.24
    æ±
    -0.23
     hey
    -0.23
    æĶ¾ä¸ĭ
    -0.23
     Commons
    -0.23
    纯æ´ģ
    -0.23
    place
    -0.22
    POSITIVE LOGITS
    åŃĢ
    0.28
    误ä¼ļ
    0.26
    umor
    0.26
    ufe
    0.25
    æĪijä»¬çŁ¥éģĵ
    0.24
     strongly
    0.24
    è£ĻåŃIJ
    0.24
     entert
    0.23
    meric
    0.23
    editable
    0.23
    Activations Density 0.031%

    No Known Activations