© 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. 9535
    Prev
    Next
    INDEX
    Explanations

    screenwriter/screenplay

    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
    ç»ıæµİä½ĵ
    -0.09
     disproportion
    -0.09
    士åħµ
    -0.09
     provid
    -0.09
    产éĶĢ
    -0.08
    ãĤŃãĥ£ãĥ³ãĥļãĥ¼ãĥ³
    -0.08
    åı¯æĢķçļĦ
    -0.08
    åħīçݯ
    -0.08
     ÙĤض
    -0.08
    -esque
    -0.08
    POSITIVE LOGITS
    çĴIJ
    0.10
    åķ·
    0.09
    UEST
    0.09
    客
    0.08
    æĺ¾å¾Ĺ
    0.08
    setError
    0.08
    esi
    0.08
    à¸īà¸ļ
    0.08
     ned
    0.08
    altar
    0.08
    Activations Density 0.021%

    No Known Activations