© 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. 50533
    Prev
    Next
    INDEX
    Explanations

    "tell us"

    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
    åĸ»
    -0.09
    ç¬ĶèĢħ
    -0.08
    åħ¶æ¬¡
    -0.08
     garner
    -0.08
    uart
    -0.08
    qe
    -0.07
    ä¸įåı¯ä»¥
    -0.07
    äºĮèĢħ
    -0.07
    人å±ħçݯå¢ĥ
    -0.07
    åıªå¾Ĺ
    -0.07
    POSITIVE LOGITS
    好åIJĹ
    0.12
    äºĨä¸įå°ij
    0.11
    åĴ±ä»¬
    0.11
    骥
    0.11
    imei
    0.10
    antha
    0.10
    å¾Ĺå¾Ī
    0.10
    åĪĨéĴŁå·¦åı³
    0.09
    åĺĽ
    0.09
    æĤ¬
    0.09
    Activations Density 0.040%

    No Known Activations