© 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. 88992
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    isode
    -0.25
    done
    -0.25
    æݨèįIJéĺħ读
    -0.24
    æĬĸéŁ³
    -0.24
    à¹ģละà¸ģาร
    -0.24
    åıijå±ķè§ĦåĪĴ
    -0.23
    chrono
    -0.22
    ?",
    -0.22
    è¿IJèIJ¥ç®¡çIJĨ
    -0.22
    dad
    -0.22
    POSITIVE LOGITS
     Irma
    0.29
    totalCount
    0.28
     totalCount
    0.26
    lene
    0.26
     totally
    0.25
     sting
    0.24
    .Count
    0.23
    mour
    0.23
     możli
    0.23
    鸢
    0.23
    Activations Density 0.013%

    No Known Activations