© 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. 112940
    Prev
    Next
    INDEX
    Explanations

    Technical writing

    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
     abl
    -0.25
    ched
    -0.25
    self
    -0.25
    æĢİä¹Īæł·
    -0.24
    clair
    -0.24
    æŬ
    -0.24
    geführt
    -0.23
    achten
    -0.23
     cl
    -0.23
    ạ
    -0.23
    POSITIVE LOGITS
    èĪį
    0.24
    enko
    0.24
    -Key
    0.23
     partido
    0.23
     Remaining
    0.22
    sgi
    0.22
     cámara
    0.22
    onica
    0.22
    é£Ľãģ³
    0.22
    odal
    0.22
    Activations Density 0.000%

    No Known Activations