© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6795
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
     fal
    -0.09
    åIJĮåŁİ
    -0.09
    èĪĽ
    -0.09
    çĶ©
    -0.09
    åIJģ
    -0.08
    æľį
    -0.08
    abor
    -0.08
    inters
    -0.08
    eren
    -0.08
    深深
    -0.08
    POSITIVE LOGITS
    åIJįå¸Ī
    0.09
    cheme
    0.09
    ç²Ĺ
    0.08
    çĺ¦
    0.08
    å©Ĩ
    0.08
     brut
    0.08
    æĿĢ
    0.08
    éļIJèĶ½
    0.08
    çī¹æľĹ
    0.08
    è¾IJ
    0.07
    Activations Density 0.023%

    No Known Activations