© 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. 21309
    Prev
    Next
    INDEX
    Explanations

    Motley Crue

    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
    HONE
    -0.11
    èĿĩ
    -0.10
    ãģĹãĤĩãģĨ
    -0.09
    è¯Ĵ
    -0.09
    夺
    -0.09
    /cop
    -0.08
    Subtitle
    -0.08
    åģ¥
    -0.08
    并å°Ĩ
    -0.08
    æĺİæĺİ
    -0.08
    POSITIVE LOGITS
    edin
    0.11
    kas
    0.10
    icz
    0.09
    otts
    0.09
     Chance
    0.09
    ASH
    0.09
    æ·ĭ
    0.09
    (er
    0.09
    URLRequest
    0.09
    ety
    0.09
    Activations Density 0.003%

    No Known Activations