© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22150
    Prev
    Next
    INDEX
    Explanations

    narrow or refine selections

    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
    è°Ħ
    -0.10
    runner
    -0.09
     Fleet
    -0.09
    åħ¨å¥Ĺ
    -0.08
    ayı
    -0.08
    çļĦä¸ĢäºĽ
    -0.08
    主æīĵ
    -0.08
    è¿ĻåĿĹ
    -0.08
    åħ¨åľº
    -0.08
    crate
    -0.08
    POSITIVE LOGITS
    é¹ŀ
    0.10
    _BIG
    0.09
    itta
    0.09
    å¾Ĺä¸įåĪ°
    0.09
    åħ³æ³¨åº¦
    0.09
    ä¸ĭãģĴ
    0.08
    artz
    0.08
    eden
    0.08
    é³ħ
    0.08
     selections
    0.08
    Activations Density 0.011%

    No Known Activations