© 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. 49679
    Prev
    Next
    INDEX
    Explanations

    right place

    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
    aign
    -0.09
    æĪ¢
    -0.08
    â»
    -0.08
    åĽ½ç±į
    -0.08
    UnderTest
    -0.08
    sus
    -0.08
     necessarily
    -0.08
    No
    -0.07
    éĩįç£ħ
    -0.07
    é£ĵ
    -0.07
    POSITIVE LOGITS
    è¦Ĩ
    0.11
    æģŃ
    0.10
    çİĭèĢħ
    0.10
    æĥ³ä¸įåĪ°
    0.09
    EMPL
    0.09
    交æĺĵå¹³åı°
    0.09
    зов
    0.09
    ë²Į
    0.09
    æ§
    0.09
    羣æŃ£åģļåĪ°
    0.09
    Activations Density 0.022%

    No Known Activations