© 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. 19877
    Prev
    Next
    INDEX
    Explanations

    AI algorithms and techniques

    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
    èĤ©è´Ł
    -0.08
    æ¸ł
    -0.08
    unal
    -0.08
    ãĥģãĥ£ãĥ³
    -0.08
    便äºİ
    -0.08
    ãĤĦãģĻ
    -0.08
     ceremon
    -0.08
    æķŀ
    -0.08
    éĩijéĵ¶
    -0.08
     Skywalker
    -0.08
    POSITIVE LOGITS
    ç®Ĺæ³ķ
    0.16
     algorithms
    0.14
     algorithm
    0.12
     techniques
    0.10
     intelligence
    0.10
     ìķĮê³ł
    0.10
    æĻºèĥ½
    0.10
    人工æĻºèĥ½
    0.10
    强大
    0.10
     based
    0.10
    Activations Density 0.382%

    No Known Activations