© 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. 48700
    Prev
    Next
    INDEX
    Explanations

    Bethlehem firm

    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
    icular
    -0.09
    EventManager
    -0.09
    éĤ¸
    -0.09
    çijļ
    -0.09
    æĪ·ç±į
    -0.09
    оÑĤов
    -0.09
    æ²»å®ī
    -0.09
    æĺī
    -0.09
    rh
    -0.09
    åħ±åĴĮ
    -0.09
    POSITIVE LOGITS
    ä¸Ģä¸Ŀ
    0.10
    人éĥ½
    0.08
     mild
    0.08
    пал
    0.08
    æ·±æĥħ
    0.08
    è½½
    0.08
    ambia
    0.08
    æİ°
    0.08
    å½ĵåľ°
    0.07
     Highlands
    0.07
    Activations Density 0.003%

    No Known Activations