© 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. 37660
    Prev
    Next
    INDEX
    Explanations

    over

    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
    夷
    -0.09
    sted
    -0.09
    Ñģал
    -0.09
    sts
    -0.09
    ieren
    -0.09
    ier
    -0.08
    æĦīæĤ¦
    -0.08
    èĦ±é¢ĸèĢĮåĩº
    -0.08
    ä¸ĢæĬĬ
    -0.08
    ä»įå°Ĩ
    -0.08
    POSITIVE LOGITS
    oze
    0.10
    empt
    0.09
    æµ·æ°´
    0.09
    çīŁ
    0.09
    çĻ»
    0.09
    èįª
    0.09
    _lhs
    0.09
    estre
    0.09
    æ´
    0.09
    ç»Ļä½łä»¬
    0.09
    Activations Density 0.024%

    No Known Activations