© 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. 8284
    Prev
    Next
    INDEX
    Explanations

    license

    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
    ness
    -0.11
    oris
    -0.10
    ish
    -0.09
    é³Į
    -0.09
    ä¸Ģæīĭ
    -0.09
     полÑĮзÑĥ
    -0.08
    sville
    -0.08
    unami
    -0.08
    ilate
    -0.08
    è§Ħç«ł
    -0.08
    POSITIVE LOGITS
    éħIJ
    0.10
    ably
    0.10
    0.09
    ator
    0.09
    ants
    0.09
    æĹłå¿§
    0.09
    åıijå±ķéĺ¶æ®µ
    0.09
    ability
    0.09
    æľīèĥ½åĬĽ
    0.08
    æľīæĦıä¹ī
    0.08
    Activations Density 0.091%

    No Known Activations