© 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. 19915
    Prev
    Next
    INDEX
    Explanations

    car makers

    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
    å©ī
    -0.09
    æģ¤
    -0.09
    ç»ı常
    -0.08
    æ·«
    -0.08
     lá»Ļ
    -0.08
     merc
    -0.08
    éĺģ
    -0.08
    æݥ触åĪ°
    -0.08
     hob
    -0.08
    åį°åĪ·
    -0.08
    POSITIVE LOGITS
    åĵģçīĮçļĦ
    0.13
    åı¬åĽŀ
    0.12
    å·¥åİĤ
    0.11
    åĵģçīĮ
    0.10
    çĶŁäº§åĴĮ
    0.10
    çĶŁäº§åŁºåľ°
    0.10
    æ¦Ķ
    0.10
    åħ¨ä½ĵåijĺå·¥
    0.10
    çĶŁäº§
    0.10
    ãĥĸãĥ©ãĥ³ãĥī
    0.10
    Activations Density 0.209%

    No Known Activations