© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 18033
    Prev
    Next
    INDEX
    Explanations

    earned distinction

    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
     Gos
    -0.09
    acies
    -0.09
    ä¸ĢåĽ¢
    -0.09
    æŁĶ
    -0.08
    æĮĩ导
    -0.08
    éļ§
    -0.08
    æĦļ
    -0.08
    å¤ļ人
    -0.08
     forwards
    -0.08
    å¯ĵ
    -0.08
    POSITIVE LOGITS
     earned
    0.16
    earned
    0.15
     merit
    0.14
     Earn
    0.13
    Earn
    0.12
    æ±Ĺæ°´
    0.12
    äºīåıĸ
    0.12
    åĭ¤åĬ³
    0.12
    éĿł
    0.12
    æīĵæĭ¼
    0.12
    Activations Density 0.095%

    No Known Activations