© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 4858
    Prev
    Next
    INDEX
    Explanations

    statue, pedestal, memorial, park, day

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èģĮå·¥
    -0.09
    éĺĸ
    -0.09
    TypeDef
    -0.09
    éĴµ
    -0.09
    éĻªä¼´
    -0.09
    åľºåĿĩ
    -0.08
    (vo
    -0.08
     todd
    -0.08
    cerer
    -0.08
    toc
    -0.08
    POSITIVE LOGITS
    éĽķåĥı
    0.16
    éĽķå¡ij
    0.14
    纪念ç¢ij
    0.13
     plaque
    0.13
    ç¢ij
    0.13
    纪念
    0.12
     statue
    0.11
     statues
    0.11
     Statue
    0.10
    åħ¬åĽŃ
    0.10
    Activations Density 0.283%

    No Known Activations