© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 62552
    Prev
    Next
    INDEX
    Explanations

    lineup

    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
    ä¸ĢåĪ»
    -0.11
    okers
    -0.10
    çĸ«æĥħæľŁéĹ´
    -0.10
    æ¸Ķæ°ij
    -0.10
    çĸ«æĥħå½±åĵį
    -0.09
    ãģªãĤĭ
    -0.09
    è°¨æħİ
    -0.09
    ãģ¾ãģ¾
    -0.09
    åīįæıIJæĺ¯
    -0.09
    å¾Īæ·±
    -0.09
    POSITIVE LOGITS
    ä¾Ŀ次
    0.09
    ç»Ħéķ¿
    0.09
    ä¸įä½³
    0.09
    eps
    0.09
    amiento
    0.09
    åĪ·
    0.08
    -sama
    0.08
    æĽĻ
    0.08
    ingo
    0.08
    à²ł
    0.08
    Activations Density 0.004%

    No Known Activations