© 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. 113031
    Prev
    Next
    INDEX
    Explanations

    you/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
    ä½ķå¤Ħ
    -0.27
     dotyc
    -0.26
    饰æ¼Ķ
    -0.25
    åıªèĥ½è¯´
    -0.25
    è¡·
    -0.24
    åĽłä¸ºå¥¹
    -0.24
    主è¦ģåİŁåĽł
    -0.24
    Function
    -0.24
    éŃĤ
    -0.23
    .reason
    -0.23
    POSITIVE LOGITS
    æį¢
    0.28
     smoothing
    0.27
    reo
    0.27
    aho
    0.25
    .sm
    0.25
    lop
    0.25
    æıĽ
    0.24
    åı¦è¡Į
    0.24
    å¾®
    0.24
    ekte
    0.23
    Activations Density 0.006%

    No Known Activations