© 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. 57747
    Prev
    Next
    INDEX
    Explanations

    condition impaired

    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
    éĥ½æĺ¯éĿŀ常
    -0.11
    èĩªæķij
    -0.10
    å®ľ
    -0.09
    å¹´ä¹ĭ
    -0.09
     ÙĦÙĩا
    -0.09
    è°
    -0.08
    éĨ®
    -0.08
    UNUSED
    -0.08
    è²¼
    -0.08
     полиÑĤик
    -0.08
    POSITIVE LOGITS
    åıĹåĪ°å½±åĵį
    0.13
    åıĹå½±åĵį
    0.11
    åıĹåĪ°
    0.11
    å½±åĵį
    0.10
    åĨ²åĩ»
    0.10
    Affected
    0.10
    æŃª
    0.09
    åıĹåĪ°äºĨ
    0.09
    严éĩį
    0.09
    éģŃåĪ°
    0.09
    Activations Density 0.159%

    No Known Activations