© 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. 20793
    Prev
    Next
    INDEX
    Explanations

    prior to

    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
    æĩ
    -0.09
    æİł
    -0.09
    _PLACE
    -0.09
    rosso
    -0.09
    èĭ¦
    -0.09
     Lomb
    -0.09
    loh
    -0.09
    ç·£
    -0.09
    ullo
    -0.09
    ä¸ĢéĹª
    -0.09
    POSITIVE LOGITS
    éĻªä¼´
    0.10
    à¸į
    0.10
    å½»åºķ
    0.10
    æ¸ħéĨĴ
    0.09
    çĬ¬
    0.09
    èĢĨ
    0.09
    级
    0.09
    èĩĮ
    0.09
    orient
    0.08
    assa
    0.08
    Activations Density 0.020%

    No Known Activations