© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 14248
    Prev
    Next
    INDEX
    Explanations

    DVD releases and videos

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
     Disp
    -0.20
    è¿IJæ°Ķ
    -0.20
     Musk
    -0.19
    Advertisements
    -0.19
    -0.19
    ÓĢ
    -0.18
     cá»ķ
    -0.18
    OfClass
    -0.18
     nhá»ĭ
    -0.18
    忧
    -0.18
    POSITIVE LOGITS
    ä¸Ĭå¸Ĥ
    0.25
    ç¢Ł
    0.23
    å¸ĤåľºçļĦ
    0.23
    åıijè¡Į
    0.21
    èĢģ大
    0.21
    æµ·å¤ĸå¸Ĥåľº
    0.20
    è¿ĽåĨĽ
    0.20
    æĪIJåĵģ
    0.20
    åıijåĶ®
    0.20
    çĽĴ
    0.20
    Activations Density 0.015%

    No Known Activations