© 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. 97331
    Prev
    Next
    INDEX
    Explanations

    fluorescence and cells

    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
    Not in Any Lists

    No Comments

    Negative Logits
     fluent
    -0.27
    ç¥ĸ
    -0.27
    ses
    -0.27
    moid
    -0.27
     ancestral
    -0.26
     LJ
    -0.25
    ä¼ĺéĽħ
    -0.25
     slab
    -0.25
    ǧ
    -0.24
     Soph
    -0.24
    POSITIVE LOGITS
    ç·£
    0.28
    ÄĪ
    0.28
    oen
    0.27
    èĦĪ
    0.26
     há»įp
    0.25
    ighter
    0.25
    antar
    0.24
    URA
    0.24
    CEPTION
    0.24
    outh
    0.24
    Activations Density 0.054%

    No Known Activations