© 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. 131244
    Prev
    Next
    INDEX
    Explanations

    code and identifiers

    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
    çĸ¾çĹħçļĦ
    -0.26
    æīĵæĸŃ
    -0.26
     Mum
    -0.26
     tempt
    -0.26
    uber
    -0.25
    haps
    -0.24
    (identity
    -0.24
    ForObject
    -0.24
    ema
    -0.23
    Zh
    -0.23
    POSITIVE LOGITS
    лав
    0.31
    rega
    0.26
     concerned
    0.24
    asje
    0.23
    .snp
    0.23
    attended
    0.23
     Nets
    0.23
     acomp
    0.22
    -arrow
    0.22
    è¾²
    0.22
    Activations Density 0.000%

    No Known Activations