© 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. 38558
    Prev
    Next
    INDEX
    Explanations

    still produces or is

    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
    åīįä¸ĸ
    -0.11
    æ²½
    -0.10
    å¹³æŶ
    -0.09
    æīĭ游
    -0.09
    åħħåĪĨä½ĵçİ°
    -0.09
    æĽ´åĥıæĺ¯
    -0.09
    è¿ij代
    -0.09
    åİŁæĿ¥æĺ¯
    -0.09
    æĬĢæľ¯çłĶåıij
    -0.09
    æĹ¢æĺ¯
    -0.09
    POSITIVE LOGITS
    è¿Ļç§įæĥħåĨµ
    0.09
    è¿Ļç§į
    0.09
    为æŃ¢
    0.09
    vens
    0.09
    tics
    0.09
    -employed
    0.08
    _activ
    0.08
    åģ¶å°Ķ
    0.08
    éĿ¢åĮħ
    0.08
     Jeg
    0.08
    Activations Density 0.038%

    No Known Activations