© 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. 2317
    Prev
    Next
    INDEX
    Explanations

    system and its following words

    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
    енн
    -0.09
    æī«ä¸Ģæī«
    -0.09
    å§Ķç»Ħç»ĩ
    -0.08
    èģĮèĥ½éĥ¨éŨ
    -0.08
    ä¸Ĭå¹´
    -0.08
    iable
    -0.08
    ÑĢаж
    -0.08
    æĪ¾
    -0.08
    ãĤµãĤ¤
    -0.08
    çŀĴ
    -0.08
    POSITIVE LOGITS
    atics
    0.18
    atic
    0.13
    ATIC
    0.12
    atis
    0.11
    atically
    0.10
    UnderTest
    0.10
    tha
    0.10
     безопаÑģноÑģÑĤи
    0.10
    (system
    0.09
    atische
    0.09
    Activations Density 0.146%

    No Known Activations