© 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. 86971
    Prev
    Next
    INDEX
    Explanations

    Alternatives and modifications

    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
    ãģĭãĤĬ
    -0.26
     extern
    -0.25
    .toolbox
    -0.25
     made
    -0.25
     be
    -0.25
     Ask
    -0.24
    èĢģçĪ·
    -0.23
    Pont
    -0.23
     in
    -0.23
     siêu
    -0.23
    POSITIVE LOGITS
    oxid
    0.33
     oxid
    0.27
    iÃŁ
    0.26
    isel
    0.26
    jin
    0.26
    jp
    0.26
    oram
    0.26
    çģµéŃĤ
    0.26
     hor
    0.24
    纵深
    0.24
    Activations Density 0.061%

    No Known Activations