© 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. 11002
    Prev
    Next
    INDEX
    Explanations

    is/’s followed by adjective or noun

    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
    -0.10
    éĤ£ä½ł
    -0.10
    æīĢåľ¨çļĦ
    -0.09
    ÙĬÙĨا
    -0.09
    ligt
    -0.09
    cestor
    -0.09
    pus
    -0.09
    åĮºåŁŁæĢ§
    -0.09
    æĶĴ
    -0.09
    æłĮ
    -0.09
    POSITIVE LOGITS
    ement
    0.08
    çĤ¹åĩ»æŁ¥çľĭ
    0.08
    身å¿ĥ
    0.08
    EDIA
    0.08
    ä¸ĩåĪĨ
    0.08
    ivalent
    0.08
    emann
    0.08
    chai
    0.08
    è¿ĻæŶåĢĻ
    0.07
     Со
    0.07
    Activations Density 0.044%

    No Known Activations