© 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. 22892
    Prev
    Next
    INDEX
    Explanations

    refrigerator / freezer

    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«ĸ
    -0.11
    æĥ³åĬŀæ³ķ
    -0.10
    æ²Ļ滩
    -0.09
    çĽĹ
    -0.09
     пÑĢог
    -0.09
    åijĽ
    -0.09
    æīĵçIJĥ
    -0.09
    滩
    -0.08
    aten
    -0.08
     effort
    -0.08
    POSITIVE LOGITS
    åĨ°
    0.11
    åľ¨å®¶éĩĮ
    0.11
    åĨ°ç®±
    0.11
    åľ¨å®¶
    0.10
     Refriger
    0.10
    åĨ·èĹı
    0.09
    /free
    0.09
    æĭİ
    0.09
    ä¹ĭéģĵ
    0.09
    åľ¨åŃ¦æł¡
    0.09
    Activations Density 0.005%

    No Known Activations