© 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. 51830
    Prev
    Next
    INDEX
    Explanations

    dragon inn

    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
    è¿·
    -0.08
    龸çİĭ
    -0.08
    åѦä½į
    -0.08
    åĿIJçĿĢ
    -0.08
    èĤ¤èī²
    -0.08
    çĿ«æ¯Ľ
    -0.08
    èĢĦ
    -0.08
    è¿·æĥij
    -0.08
    èĪľ
    -0.08
     пÑĢедназнаÑĩен
    -0.08
    POSITIVE LOGITS
    odox
    0.10
    ICC
    0.09
    骰
    0.09
    修士
    0.09
    éĿ¢åĮħ
    0.09
    çī¹ä»·
    0.08
    çıŃ
    0.08
    è´©
    0.08
     Ars
    0.08
    éī´å®ļ
    0.08
    Activations Density 0.083%

    No Known Activations