© 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. 21821
    Prev
    Next
    INDEX
    Explanations

    capital gains tax

    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
    çŃĴ
    -0.10
    æĬ¢
    -0.09
    åĮł
    -0.09
    æ½®æµģ
    -0.09
    åĪº
    -0.08
     deb
    -0.08
    æĢ»äº§åĢ¼
    -0.08
    _nh
    -0.08
    çĶĦ
    -0.08
    æĬ¢åįł
    -0.08
    POSITIVE LOGITS
    åįĸåĩº
    0.10
    éĺļ
    0.10
    åįĹè·¯
    0.09
    iske
    0.09
    çĶ³
    0.09
    à¸Ĺา
    0.09
    liner
    0.09
     bre
    0.09
     barg
    0.09
    èij±
    0.08
    Activations Density 0.032%

    No Known Activations