© 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. 110915
    Prev
    Next
    INDEX
    Explanations

    decisions and official procedures

    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
    sonian
    -0.36
    ä¼ģä¸ļåľ¨
    -0.29
    gard
    -0.27
    swer
    -0.27
    APON
    -0.26
    global
    -0.25
    tle
    -0.25
    cer
    -0.25
    -hide
    -0.25
    ancies
    -0.24
    POSITIVE LOGITS
    sav
    0.28
    esp
    0.25
    é¢Ĭ
    0.24
    0.24
     partida
    0.23
    esar
    0.23
     Nhi
    0.23
    athe
    0.23
     Attack
    0.23
    .setup
    0.23
    Activations Density 0.006%

    No Known Activations