© 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. 51940
    Prev
    Next
    INDEX
    Explanations

    why it

    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
    æĹłçĸij
    -0.09
    ä¾Ŀæŧ
    -0.08
    ãģ£ãģĵ
    -0.08
    åIJĮæĻĤãģ«
    -0.08
    inch
    -0.08
    .utcnow
    -0.08
    éĶħ
    -0.08
    emon
    -0.08
     Wish
    -0.08
    apot
    -0.08
    POSITIVE LOGITS
     but
    0.14
    ä½Ĩä»İ
    0.14
    ä½Ĩ
    0.14
    ãģ§ãģĻãģĮ
    0.13
    ä½Ĩå¦Ĥæŀľ
    0.13
    ä½Ĩåľ¨
    0.13
    ä½ĨæĪij
    0.12
     но
    0.12
    ä½Ĩ她
    0.12
    ä½Ĩä¹Ł
    0.12
    Activations Density 0.092%

    No Known Activations