© 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. 130805
    Prev
    Next
    INDEX
    Explanations

    is

    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
    èĽŁ
    -0.30
    鸳
    -0.25
    Ļ¶
    -0.25
    æĦī
    -0.25
    ]+\
    -0.24
    ackers
    -0.24
    isphere
    -0.24
     van
    -0.24
    iter
    -0.24
    iller
    -0.23
    POSITIVE LOGITS
    lessly
    0.29
    éłĤãģį
    0.27
    åŬ
    0.26
    lesi
    0.26
    âĢ¦the
    0.26
    posix
    0.26
    fully
    0.25
    å¥ļ
    0.25
     establishment
    0.25
    âĢ¦I
    0.25
    Activations Density 14.982%

    No Known Activations