© 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. 18052
    Prev
    Next
    INDEX
    Explanations

    kiosk sales

    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
    дол
    -0.10
    ä¹Łåıªæĺ¯
    -0.09
    inte
    -0.09
    å¸ĮæľĽèĥ½å¤Ł
    -0.09
    åĮºåŁŁæĢ§
    -0.08
    为æ°ij
    -0.08
    å¼ķæµģ
    -0.08
    å£ŀ
    -0.08
    档次
    -0.08
    /copyleft
    -0.08
    POSITIVE LOGITS
    â¬Ĩ
    0.12
    æĿ¥åĪ°
    0.09
    lete
    0.09
    ãģ¤ãģĭ
    0.09
    èİ·å¾ĹæĦŁ
    0.09
    üstü
    0.09
    åıijçİ°
    0.09
    çĮĽçĥĪ
    0.09
    heap
    0.08
    çİ°åŃĺ
    0.08
    Activations Density 0.007%

    No Known Activations