© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 3084
    Prev
    Next
    INDEX
    Explanations

    Trial Court

    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
    éºĵ
    -0.11
    æĴŃ
    -0.09
    @Inject
    -0.09
    _ctxt
    -0.09
    peg
    -0.09
    PCM
    -0.09
    èļĵ
    -0.09
    è¹Ħ
    -0.08
    å«©
    -0.08
    æį©
    -0.08
    POSITIVE LOGITS
    å¼ķ
    0.10
    éļ¶å±ŀ
    0.09
    ä¸Ĭå²Ĺ
    0.09
    adv
    0.09
    æŀĦæĪIJäºĨ
    0.08
    uba
    0.08
    åĹ¾
    0.08
     kn
    0.08
    æĸ°ä¸ī
    0.08
    æ²Į
    0.08
    Activations Density 0.001%

    No Known Activations