© 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. 99240
    Prev
    Next
    INDEX
    Explanations

    we

    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
     occurs
    -0.26
    åı®
    -0.26
    ROP
    -0.26
    åķ°
    -0.26
    rebbe
    -0.25
     Rhe
    -0.25
     himself
    -0.25
    oko
    -0.25
     worth
    -0.24
    Requires
    -0.23
    POSITIVE LOGITS
     ourselves
    0.43
    ä¸Ģèµ·æĿ¥
    0.35
    bserv
    0.30
    aptic
    0.29
    æĬĬå®ĥ
    0.28
    åħ±åIJĮåĬªåĬĽ
    0.28
     sobie
    0.28
    让å®ĥ
    0.27
    blink
    0.27
    å°Ĩåħ¶
    0.26
    Activations Density 0.327%

    No Known Activations