© 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. 49356
    Prev
    Next
    INDEX
    Explanations

    verify or verification

    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
    /or
    -0.10
    å¼±
    -0.10
     ÐĴлад
    -0.09
    umbing
    -0.09
    æĪijçĽ¸ä¿¡
    -0.09
     Ñĥни
    -0.09
    imes
    -0.08
    ãĥĭãĥ³ãĤ°
    -0.08
     ÑĦигÑĥÑĢ
    -0.08
     vero
    -0.08
    POSITIVE LOGITS
    ä¸Ģä¸ĭ
    0.10
    äºĨä¸Ģä¸ĭ
    0.10
    cation
    0.09
    rd
    0.09
    ãģĹ
    0.09
    ìĤ¬íķŃ
    0.09
    å¾ĹäºĨ
    0.08
    нÑĥÑĤÑĮ
    0.08
    oga
    0.08
    icle
    0.08
    Activations Density 0.016%

    No Known Activations