© 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. 99260
    Prev
    Next
    INDEX
    Explanations

    code

    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
     Viewing
    -0.25
     Kore
    -0.25
     ÐŀÑĩ
    -0.25
    .fname
    -0.25
     Fortune
    -0.24
     creds
    -0.24
     coaching
    -0.24
    egan
    -0.24
    Ñī
    -0.24
    apollo
    -0.23
    POSITIVE LOGITS
     end
    0.27
    ley
    0.27
     inse
    0.26
    LEY
    0.26
     eyes
    0.26
    _Release
    0.25
     Dict
    0.25
    elight
    0.24
    ate
    0.24
    getLast
    0.24
    Activations Density 0.000%

    No Known Activations