© 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. 9449
    Prev
    Next
    INDEX
    Explanations

    DirectX Windows SDK

    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
    Hop
    -0.09
    æݸ
    -0.09
    èį¯
    -0.09
    èĥĨ
    -0.09
    ä½ľæģ¯
    -0.09
    å®Ľ
    -0.09
     Giov
    -0.09
     Rif
    -0.09
    Scan
    -0.09
     Andr
    -0.08
    POSITIVE LOGITS
    agram
    0.10
    å·¥åķĨ
    0.10
    æ²īéĩį
    0.09
    led
    0.08
    hl
    0.08
    æīĵ交éģĵ
    0.08
    éĩįåŀĭ
    0.08
     Omn
    0.08
    å·¡
    0.08
    æĶ¹è£ħ
    0.08
    Activations Density 0.404%

    No Known Activations