© 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. 8419
    Prev
    Next
    INDEX
    Explanations

    issue reporting or links

    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
    -Ta
    -0.09
    çĥĿ
    -0.09
    .hashCode
    -0.09
    çļĦå°±æĺ¯
    -0.09
    ä¹ĭæĺŁ
    -0.08
     Andersen
    -0.08
    æ¸ħæ¥ļ
    -0.08
    表çĻ½
    -0.08
    eti
    -0.08
    phon
    -0.08
    POSITIVE LOGITS
    è´²
    0.09
    ä¸ļ
    0.09
    èĤ¤
    0.09
    overs
    0.09
    ville
    0.08
    éĢŃ
    0.08
    饱
    0.08
    衬
    0.08
    VILLE
    0.08
    æķĻä¼ļ
    0.08
    Activations Density 0.006%

    No Known Activations