© 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. 113096
    Prev
    Next
    INDEX
    Explanations

    a

    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
    uve
    -0.32
    ué
    -0.29
    aley
    -0.28
    ней
    -0.27
     Omn
    -0.26
     prop
    -0.25
    noc
    -0.25
    UEST
    -0.25
     Accepted
    -0.24
    ebra
    -0.24
    POSITIVE LOGITS
    TypeID
    0.25
    DBNull
    0.25
    compound
    0.24
    ind
    0.24
    ont
    0.24
    one
    0.24
    æľªæĿ¥åıijå±ķ
    0.24
     Village
    0.24
     cena
    0.24
     Features
    0.23
    Activations Density 0.023%

    No Known Activations