© 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. 20798
    Prev
    Next
    INDEX
    Explanations

    table with context

    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
    æıĦ
    -0.10
    çĵ£
    -0.09
    jav
    -0.09
    éĽĨè£ħ
    -0.09
     gözü
    -0.09
    ----------------------------------------------------------------
    -0.09
    åĹĵåŃIJ
    -0.09
    管线
    -0.09
    æĺ¯éŁ©åĽ½
    -0.08
    åĪ¹éĤ£
    -0.08
    POSITIVE LOGITS
    .Table
    0.13
    [table
    0.11
    æ¡Į
    0.11
    /table
    0.11
    .TABLE
    0.11
    (Table
    0.10
    .table
    0.10
    cloth
    0.10
    .CreateTable
    0.10
    (table
    0.10
    Activations Density 0.018%

    No Known Activations