© 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. 129250
    Prev
    Next
    INDEX
    Explanations

    Scientific research

    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
    -cross
    -0.28
    _cross
    -0.27
    åı«
    -0.27
    jer
    -0.26
     crosses
    -0.25
    CHA
    -0.25
     ministry
    -0.25
    åĢĴ
    -0.25
    ippo
    -0.25
    anol
    -0.24
    POSITIVE LOGITS
    究
    0.25
    ltk
    0.25
    renc
    0.25
     prescribe
    0.25
    NSS
    0.24
    æĦıä¹īä¸Ĭ
    0.24
    管åĪ¶
    0.24
    oks
    0.23
    è£ģåĪ¤
    0.23
     Nass
    0.23
    Activations Density 29.522%

    No Known Activations