© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 36838
    Prev
    Next
    INDEX
    Explanations

    guinea pigs

    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
    инÑĭ
    -0.10
    inesis
    -0.09
    IZER
    -0.09
    lek
    -0.09
     Breath
    -0.08
     intact
    -0.08
    é©°
    -0.08
    æ¶ķ
    -0.08
    eyer
    -0.08
    cuts
    -0.08
    POSITIVE LOGITS
    æĭ³
    0.10
    å¿«æĿ¥
    0.09
    elen
    0.09
    åķĸ
    0.09
    éģĵçIJĨ
    0.08
    ais
    0.08
    .self
    0.08
    骥
    0.08
    ä¾Ħ
    0.08
    æŃ¦å£«
    0.08
    Activations Density 0.008%

    No Known Activations