© 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. 129287
    Prev
    Next
    INDEX
    Explanations

    single digit numbers

    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
    åIJ²
    -0.28
    uard
    -0.25
    theid
    -0.25
    azy
    -0.24
    inds
    -0.24
    EMU
    -0.24
    ascal
    -0.24
    umble
    -0.24
    (yy
    -0.24
    æ¯ħåĬĽ
    -0.23
    POSITIVE LOGITS
    body
    0.27
    æµĬ
    0.26
     proof
    0.25
    Portal
    0.25
    quiv
    0.24
    le
    0.24
     reduce
    0.24
    us
    0.23
     mã
    0.23
    åı¯ä»¥è®©
    0.23
    Activations Density 0.016%

    No Known Activations