© 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. 36651
    Prev
    Next
    INDEX
    Explanations

    bits and pieces

    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
    éĻĤ
    -0.09
    å¿ĥèĦıçĹħ
    -0.09
    æĤ£
    -0.09
    è·ĭ
    -0.08
    æĢģ度
    -0.08
    è°ģ
    -0.08
    è¾ĩ
    -0.08
    èµŀ
    -0.08
    åĪĨä¼ļ
    -0.08
    _backward
    -0.08
    POSITIVE LOGITS
     инÑĦоÑĢмаÑĨии
    0.11
    çīĩåŃIJ
    0.10
     pieces
    0.10
    ä¸īåĽĽ
    0.09
    çĽ¸å¹²
    0.09
     Pieces
    0.09
    mort
    0.09
    CLU
    0.09
    å°ıå¾®
    0.09
     bits
    0.09
    Activations Density 0.020%

    No Known Activations