© 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. 97059
    Prev
    Next
    INDEX
    Explanations

    ous

    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
    Negative Logits
    i
    -0.30
    tain
    -0.28
    ’s
    -0.26
    t
    -0.25
    ected
    -0.25
    ä¸ĢåįĬ
    -0.25
    gon
    -0.25
    ed
    -0.24
    OV
    -0.24
    an
    -0.24
    POSITIVE LOGITS
    ness
    0.54
    NESS
    0.42
    éĺŁéķ¿
    0.31
    ityEngine
    0.28
    chwitz
    0.28
    alis
    0.26
    è¿Ļæł·ä¸ĢæĿ¥
    0.26
    çī¹æľĹ
    0.25
    oler
    0.25
    amente
    0.25
    Activations Density 0.175%

    No Known Activations