© 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. 33126
    Prev
    Next
    INDEX
    Explanations

    phase transition temperature

    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
    ãģ°
    -0.09
    èķĸ
    -0.09
    举æĸ¹
    -0.09
    ä¹ı
    -0.09
    RelativeTo
    -0.09
     amalg
    -0.09
    ldr
    -0.08
    鸵
    -0.08
    æĥŃ
    -0.08
    æĹħ
    -0.08
    POSITIVE LOGITS
     Disorder
    0.10
    åĢĴ
    0.10
     disorder
    0.09
    errat
    0.09
    社ä¼ļç»Ħç»ĩ
    0.09
    å¯ĴåĨ¬
    0.09
    çŁ³å®¶
    0.08
    ackson
    0.08
     tilt
    0.08
    æľīåºı
    0.08
    Activations Density 0.596%

    No Known Activations