© 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. 34223
    Prev
    Next
    INDEX
    Explanations

    Marketing appoints

    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
    亲å±ŀ
    -0.10
    ities
    -0.10
    itt
    -0.10
    壤
    -0.09
    ä¸Ģå¹´ä¸Ģ度
    -0.09
    ä¸ŃåĽ½çī¹èī²
    -0.08
     ÑĥÑĢовенÑĮ
    -0.08
    éĤ°
    -0.08
    YTE
    -0.08
    ahkan
    -0.08
    POSITIVE LOGITS
    éŨåīį
    0.08
     Luna
    0.08
    è²»
    0.08
    çŃĸåĪĴ
    0.08
    -economic
    0.08
    为é¦ĸ
    0.08
    è¿ijè§Ĩ
    0.08
    忽çķ¥äºĨ
    0.08
    aira
    0.08
    é½IJ
    0.08
    Activations Density 0.012%

    No Known Activations