© 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. 39044
    Prev
    Next
    INDEX
    Explanations

    third of

    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
    å¸IJ
    -0.09
    é¹ħ
    -0.09
    antium
    -0.08
    anse
    -0.08
    ç©´
    -0.08
    åģ¾
    -0.08
    é¦ĭ
    -0.08
    iment
    -0.08
    æħĮ
    -0.08
    antine
    -0.08
    POSITIVE LOGITS
    erti
    0.10
    è²Į
    0.09
    åħ±åĴĮ
    0.08
    ä¸IJ
    0.08
     thereof
    0.08
    馥
    0.08
    åħ±åĴĮåĽ½
    0.08
    çĶļèĩ³æĺ¯
    0.08
    ,/
    0.08
    nap
    0.08
    Activations Density 0.023%

    No Known Activations