© 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. 61259
    Prev
    Next
    INDEX
    Explanations

    coincidence, chance, accident

    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
    æĺİçŁ¥
    -0.11
    桦
    -0.09
    standing
    -0.09
    æ³ķåĪ¶
    -0.09
    èĩ´åij½
    -0.09
    èĨı
    -0.08
    ëĿ½
    -0.08
    æİ
    -0.08
    _MISSING
    -0.08
    ä¸įè¦ģåĨį
    -0.08
    POSITIVE LOGITS
    å·§åIJĪ
    0.19
     coincidence
    0.15
    ety
    0.11
    mere
    0.09
    个æĢ§
    0.09
     coinc
    0.09
    èī²å½©
    0.09
    éķĴ
    0.08
    å¯Ĥ
    0.08
    çį¾
    0.08
    Activations Density 0.161%

    No Known Activations