© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37276
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases indicating separation

    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
    é£İçŃĿ
    -0.08
    зна
    -0.08
    astro
    -0.08
    aths
    -0.08
    åĪĨéħį
    -0.08
    ATH
    -0.08
    æĹ©æĻļ
    -0.08
    çĭĹ
    -0.08
    agraph
    -0.08
    交代
    -0.08
    POSITIVE LOGITS
    羣æŃ£çļĦ
    0.12
    æ¶İ
    0.11
    寻常
    0.09
    .until
    0.09
    åŀ«
    0.09
    åĨµä¸Ķ
    0.09
    ä½ķåĨµ
    0.09
    .lin
    0.09
    æĽ´ä½ķåĨµ
    0.09
    踵
    0.09
    Activations Density 0.093%

    No Known Activations