© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37873
    Prev
    Next
    INDEX
    Explanations

    clarification sections

    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
    çĦļçĥ§
    -0.11
    ogle
    -0.11
    rone
    -0.11
    é©·
    -0.10
    åĵij
    -0.10
    å½ĴæĿ¥
    -0.10
    ãģĵãģ¨ãĤĴ
    -0.10
    ä¸įçĪ±
    -0.10
    \Factories
    -0.10
    è¿ĻèĪ¬
    -0.10
    POSITIVE LOGITS
    æĮĩçļĦæĺ¯
    0.09
    æĺ¯æĮĩ
    0.08
     Vision
    0.08
     refers
    0.08
     Arch
    0.07
     through
    0.07
    对æİ¥
    0.07
     rar
    0.07
     easy
    0.07
    ä½ĵçİ°åľ¨
    0.07
    Activations Density 0.190%

    No Known Activations