© 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. 22-TRANSCODER-HP
    7. 129277
    Prev
    Next
    INDEX
    Explanations

    legal/abstract vocabulary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +p
    -0.28
     beaut
    -0.27
    utes
    -0.27
    +v
    -0.27
    æĭĸ
    -0.25
    ieres
    -0.25
    ingly
    -0.25
    uç
    -0.24
    utra
    -0.24
    act
    -0.24
    POSITIVE LOGITS
    ness
    0.36
    NESS
    0.33
     enough
    0.32
    èĭ¥æĤ¨
    0.30
     Enough
    0.29
    ities
    0.28
     Spot
    0.28
    åıĪæľī
    0.27
    ·¨
    0.26
     spot
    0.26
    Activations Density 0.156%

    No Known Activations