© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9764
    Prev
    Next
    INDEX
    Explanations

    view the

    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
    exus
    -0.09
    æµ´
    -0.08
    åħ¬æ°ij
    -0.08
    ç¾½
    -0.08
    éĹªåħī
    -0.08
    é»ij马
    -0.08
    _SM
    -0.08
    wers
    -0.08
    åłª
    -0.08
    çıįè´µ
    -0.08
    POSITIVE LOGITS
    çľ¼åīįçļĦ
    0.09
    å³Ĵ
    0.09
    iel
    0.08
    -uri
    0.08
     Affero
    0.08
    çIJĨèµĶ
    0.08
     themed
    0.08
    ç¡®å®ļ
    0.08
    ç»Ŀ
    0.08
    립
    0.08
    Activations Density 0.005%

    No Known Activations