© 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. 99220
    Prev
    Next
    INDEX
    Explanations

    are

    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
    ->$
    -0.28
    åħĥå®Ŀ
    -0.26
    æĺİæĺ¾
    -0.26
     fat
    -0.25
     Keystone
    -0.25
    Highest
    -0.25
    still
    -0.24
    ï¼Į“
    -0.24
     hesitate
    -0.24
    emacs
    -0.24
    POSITIVE LOGITS
    -pic
    0.28
    ãģĤãĤĭ
    0.28
    ERING
    0.27
    åı¦ä¸Ģç§į
    0.27
    uffle
    0.27
    =Value
    0.26
    éĤ£æŶåĢĻ
    0.25
    çģµåĬ¨
    0.25
    éłĨ
    0.25
    tti
    0.25
    Activations Density 0.017%

    No Known Activations