© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12323
    Prev
    Next
    INDEX
    Explanations

    about sections

    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
     push
    -0.22
     à¸ŀฤษ
    -0.21
     claim
    -0.21
    å¥Ķ
    -0.20
     PaÅĦstwo
    -0.20
     claiming
    -0.19
    l
    -0.19
     actually
    -0.19
    æĹ¢
    -0.19
     มà¸ģร
    -0.19
    POSITIVE LOGITS
     spep
    0.22
     taxp
    0.22
    PointerException
    0.21
     ÑģобÑģÑĤвенно
    0.20
     Tiffany
    0.20
    éģIJ
    0.19
    æ½Ķ
    0.19
    æľįåĬ¡ä½ĵç³»
    0.19
    ampie
    0.18
     newcom
    0.18
    Activations Density 0.010%

    No Known Activations