© 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. 111252
    Prev
    Next
    INDEX
    Explanations

    negation

    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
    红æĺŁ
    -0.25
    ä¸įä»ħæĺ¯
    -0.25
    _REQUIRE
    -0.24
    åIJĪæ³ķæĢ§
    -0.24
    çļĦè¦ģæ±Ĥ
    -0.24
    unday
    -0.24
    proved
    -0.23
    prüf
    -0.23
    æĢ»æī¿åĮħ
    -0.23
    .CreateCommand
    -0.23
    POSITIVE LOGITS
    thalm
    0.31
     mere
    0.27
     Vox
    0.27
     undis
    0.25
     STATIC
    0.25
     limited
    0.24
    æľīéĻIJ
    0.24
    vig
    0.24
    è·ij
    0.24
    èģĤ
    0.24
    Activations Density 0.003%

    No Known Activations