© 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. 9653
    Prev
    Next
    INDEX
    Explanations

    alkaline and suffixes

    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
    ina
    -0.09
    çľļ
    -0.09
    ãĤĭãģ®ãģĮ
    -0.09
    mai
    -0.08
    éŀĭåŃIJ
    -0.08
    æ£į
    -0.08
    æłĪ
    -0.08
     penal
    -0.08
     Ru
    -0.08
    æ¯ĭ
    -0.08
    POSITIVE LOGITS
    éĵĽ
    0.11
    atory
    0.10
    媵
    0.09
    èĢIJçĶ¨
    0.08
    çĸĹæ³ķ
    0.08
    åľ£
    0.08
     pont
    0.08
    icy
    0.08
    è¿Ļä¹Īåģļ
    0.08
     FRIEND
    0.08
    Activations Density 0.046%

    No Known Activations