© 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. 111095
    Prev
    Next
    INDEX
    Explanations

    code identifiers

    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
    è¡ĮæĶ¿éĥ¨éŨ
    -0.27
    麼
    -0.26
    ä»Ģä¹ĪæĦıæĢĿ
    -0.26
    亲æĪļ
    -0.25
     neglig
    -0.24
     Reco
    -0.24
    )”
    -0.24
    ’a
    -0.24
    ä¹Ī
    -0.24
     ornament
    -0.24
    POSITIVE LOGITS
    osti
    0.32
    hyp
    0.29
    æ´¥
    0.28
    (stdout
    0.27
    Ø¡
    0.26
    оÑģÑĤÑĮ
    0.26
    omid
    0.25
    Enabled
    0.24
    ä¸ĢæľŁ
    0.24
    .firebaseio
    0.24
    Activations Density 0.027%

    No Known Activations