© 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. 48267
    Prev
    Next
    INDEX
    Explanations

    see what happens

    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
     Gaz
    -0.10
    1
    -0.08
    ä½łçŁ¥éģĵ
    -0.08
    åıªè¦ģ
    -0.08
    esch
    -0.08
     Hers
    -0.08
    åıªè¦ģä½ł
    -0.08
    ume
    -0.07
    ijo
    -0.07
     perpetual
    -0.07
    POSITIVE LOGITS
    ç¾İæľ¯é¦Ĩ
    0.12
    åŁİå¸Ĥåıijå±ķ
    0.11
    è¿Ļ件
    0.10
    дей
    0.10
    æŶéĹ´åĴĮ
    0.10
    åĺ´
    0.10
    å¼¼
    0.10
    è¿Ļæī¹
    0.10
    ä¸įæĸŃåıijå±ķ
    0.10
    è·Ħ
    0.10
    Activations Density 0.012%

    No Known Activations