© 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. 53039
    Prev
    Next
    INDEX
    Explanations

    expectations versus reality

    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
    æıIJ示
    -0.10
    æݨèįIJéĺħ读
    -0.09
    hints
    -0.09
    .singleton
    -0.09
    åłĨæĶ¾
    -0.08
    ÑĨеп
    -0.08
    äºĨåIJ§
    -0.08
    .partial
    -0.08
    åĢĻ
    -0.08
    WithEmail
    -0.08
    POSITIVE LOGITS
    æĩ¦
    0.09
    owi
    0.09
    æľĪåĪĿ
    0.09
    ka
    0.08
    éħį
    0.08
     earlier
    0.08
    scope
    0.08
    arts
    0.08
    å½»
    0.08
    åħļæĢ»
    0.08
    Activations Density 0.021%

    No Known Activations