© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 408
    Prev
    Next
    INDEX
    Explanations

    to top

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    åIJĵ
    -0.25
    Ñĥз
    -0.24
    pons
    -0.23
    Ĭ¶
    -0.23
    ä¸įæĩĤ
    -0.23
    ä¸įéĻIJ
    -0.23
    inces
    -0.23
    æĦŁåħ´è¶£çļĦ
    -0.22
    ,,
    -0.22
    é¹ı
    -0.22
    POSITIVE LOGITS
    ä»»ä½ķ人
    0.28
    ä¹Łä¸įåı¯èĥ½
    0.27
     anyone
    0.25
    ä¹ŁæĹłæ³ķ
    0.24
     whatsoever
    0.24
    à¹Ģลย
    0.24
     anywhere
    0.23
     anymore
    0.23
     anybody
    0.23
    _except
    0.23
    Activations Density 0.020%

    No Known Activations