© 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. 31253
    Prev
    Next
    INDEX
    Explanations

    what is expected

    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
    浸
    -0.10
    æ·«
    -0.09
    åıªè¦ģä½ł
    -0.09
    å¢ĥ
    -0.08
    éĿŀ常éĢĤåIJĪ
    -0.08
    梯
    -0.08
    å£ķ
    -0.08
    éĶĢåĶ®æ¸łéģĵ
    -0.08
    _INITIAL
    -0.08
    ãģ°
    -0.08
    POSITIVE LOGITS
     expectations
    0.15
    æľŁå¾ħ
    0.15
    æľŁæľĽ
    0.14
    ä¹łæĥ¯äºĨ
    0.13
     expectation
    0.13
     expects
    0.12
    æľŁçĽ¼
    0.12
    ä¹łæĥ¯
    0.12
    Expect
    0.11
     accustomed
    0.11
    Activations Density 0.061%

    No Known Activations