© 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. 57968
    Prev
    Next
    INDEX
    Explanations

    wood, yard, Authors, ucle

    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
    naire
    -0.10
    erb
    -0.10
    è¿Ļæł·æīįèĥ½
    -0.10
    æĥ³åĪ°
    -0.09
    interest
    -0.09
     اÙĦÙħسÙĦØŃØ©
    -0.09
    æIJĤ
    -0.08
    大å°ı
    -0.08
    çľĭä¸Ģçľĭ
    -0.08
    æĥ³æĥ³
    -0.08
    POSITIVE LOGITS
    ç¨ļ
    0.09
    åı°å·ŀ
    0.09
     disgr
    0.09
    èį§
    0.09
    å»Ĭ
    0.08
    èĥ¼
    0.08
    _logits
    0.08
    atsu
    0.08
    çı¥
    0.08
    isode
    0.07
    Activations Density 0.002%

    No Known Activations