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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37097
    Prev
    Next
    INDEX
    Explanations

    approximately or about

    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
    tip
    -0.12
    ti
    -0.09
    éĿ¢åīį
    -0.08
    Abr
    -0.08
    毡
    -0.08
    åľºåIJĪ
    -0.08
    对äºİæĪij们
    -0.08
    åij½è¿IJ
    -0.08
    åıĭæĥħ
    -0.08
    éĩľ
    -0.08
    POSITIVE LOGITS
    enor
    0.08
    alah
    0.08
    imately
    0.08
    ä¸įå®ļ
    0.08
    çĢı
    0.08
     slate
    0.08
     manh
    0.08
    ainter
    0.08
    ADVERTISEMENT
    0.08
    encers
    0.08
    Activations Density 0.086%

    No Known Activations