© 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. 52344
    Prev
    Next
    INDEX
    Explanations

    ready for

    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
    åģļçļĦäºĭ
    -0.10
    æĢ»æľī
    -0.09
    åģļçļĦäºĭæĥħ
    -0.09
    ahl
    -0.09
    ç¦ħ
    -0.09
    åĽ½å®ī
    -0.09
    MA
    -0.09
    ç´łè´¨æķĻèĤ²
    -0.09
    äºĽä»Ģä¹Ī
    -0.08
    æ¯ĽçĹħ
    -0.08
    POSITIVE LOGITS
    举
    0.10
    æļ´
    0.09
    phia
    0.09
    å¼±
    0.09
    unal
    0.09
    getApplication
    0.09
    _SUP
    0.09
    itest
    0.09
    ä»ĭ
    0.08
    paid
    0.08
    Activations Density 0.007%

    No Known Activations