© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 131074
    Prev
    Next
    INDEX
    Explanations

    than

    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
    Negative Logits
    akening
    -0.30
    æ¯Ķäºļ
    -0.28
    addin
    -0.27
     soon
    -0.27
    =back
    -0.26
    åĬłç´§
    -0.26
    èijŃ
    -0.25
    åĨĴ
    -0.25
    ä»ħ次äºİ
    -0.25
     addObject
    -0.25
    POSITIVE LOGITS
     span
    0.26
    å®ļå¾ĭ
    0.24
    ento
    0.24
     mature
    0.24
     ÑģпÑĢав
    0.23
    osp
    0.23
    sein
    0.23
    ãĤĪãģĨãģ¨
    0.23
     Otherwise
    0.23
    olt
    0.23
    Activations Density 11.619%

    No Known Activations