© 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. 35528
    Prev
    Next
    INDEX
    Explanations

    talk, about, buzz

    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
    车çīĮ
    -0.10
    ä½ľèĢħæīĢæľī
    -0.10
    诡
    -0.09
    踯
    -0.09
    轸
    -0.09
    æĮĩå¼ķ
    -0.09
    æī¿
    -0.09
    ancing
    -0.08
    累累
    -0.08
    _rq
    -0.08
    POSITIVE LOGITS
    çĥŃè®®
    0.15
    è°Ī论
    0.15
    åı£ç¢ij
    0.14
    çļĦè¯Ŀé¢ĺ
    0.13
    æ´¥
    0.12
    çĥŃçĥĪ
    0.12
    è¯Ŀé¢ĺ
    0.12
     buzz
    0.12
     talk
    0.12
    buzz
    0.11
    Activations Density 0.069%

    No Known Activations