© 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. 88635
    Prev
    Next
    INDEX
    Explanations

    you

    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
    oris
    -0.27
    æľī个
    -0.26
     known
    -0.25
    agement
    -0.24
     drops
    -0.24
    ä¹ĭæīĢ以
    -0.24
    æľĭåıĭ
    -0.24
    OptionsMenu
    -0.23
    agal
    -0.23
     batching
    -0.23
    POSITIVE LOGITS
    jee
    0.28
    ilst
    0.27
    itzer
    0.25
    atetime
    0.25
    anything
    0.25
    quat
    0.24
    å°½
    0.24
     Uncategorized
    0.24
    å±Ģéķ¿
    0.24
     Anything
    0.24
    Activations Density 0.034%

    No Known Activations