© 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. 87131
    Prev
    Next
    INDEX
    Explanations

    is

    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
    ä½ķåĨµ
    -0.33
    æĥħåĨµä¸ĭ
    -0.28
     especially
    -0.28
     Especially
    -0.28
    åĬłä¹ĭ
    -0.28
    æĽ´ä½ķåĨµ
    -0.27
    å°¤åħ¶æĺ¯åľ¨
    -0.27
    è¿
    -0.27
    åĽłä¸ºå¥¹
    -0.27
    ucha
    -0.27
    POSITIVE LOGITS
     big
    0.35
    .mapping
    0.27
     HUGE
    0.25
    big
    0.25
    å¾Īä¸įéĶĻ
    0.25
    .vstack
    0.24
     hint
    0.24
    awn
    0.24
    ä¿Ŀ驾
    0.24
    asd
    0.23
    Activations Density 0.002%

    No Known Activations