© 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. 61467
    Prev
    Next
    INDEX
    Explanations

    realize, forget, unaware, neglect

    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
    ppy
    -0.10
    åģļå·¥
    -0.09
    ä¾ĿéĿł
    -0.09
     Coupons
    -0.09
    çĿ¨
    -0.09
    ä¹Ŀ大
    -0.08
    çİ¢
    -0.08
    bia
    -0.08
    (encoding
    -0.08
    设æľī
    -0.08
    POSITIVE LOGITS
    æĦıè¯ĨåĪ°
    0.14
    注æĦıåĪ°
    0.12
    æĥ³åĪ°
    0.10
    å¿ĺè®°äºĨ
    0.10
    æ®Ĭ
    0.10
    åį´
    0.10
     realize
    0.10
    äºĨ解åĪ°
    0.09
     realise
    0.09
    æĥ³è¿ĩ
    0.09
    Activations Density 0.078%

    No Known Activations