© 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. 8947
    Prev
    Next
    INDEX
    Explanations

    rule-wise

    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
     Pavel
    -0.09
    ť
    -0.08
    ->__
    -0.08
    åģļåĪ°
    -0.08
    sett
    -0.08
    缴è§Ĥ
    -0.08
    çķĻä½ı
    -0.08
    绾
    -0.08
    دع
    -0.08
     авÑĤом
    -0.08
    POSITIVE LOGITS
    åŃĺåľ¨äºİ
    0.10
    ä½ĵçİ°åľ¨
    0.09
    uhe
    0.09
    flen
    0.09
    blick
    0.09
    olec
    0.09
    èİ«è¿ĩäºİ
    0.08
    峤
    0.08
     Peters
    0.08
    PAIR
    0.08
    Activations Density 0.454%

    No Known Activations