© 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. 13231
    Prev
    Next
    INDEX
    Explanations

    song titles and band names

    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
    æĻļå¹´
    -0.21
    éĿŀæ´²
    -0.21
    stead
    -0.20
    Cop
    -0.19
    åİŁæ²¹
    -0.19
    æĺĤ
    -0.19
    èĤ¥
    -0.19
    äº§åľ°
    -0.19
    ä¼°
    -0.18
    享
    -0.18
    POSITIVE LOGITS
    ç»ĿæľĽ
    0.21
    åĨ²åĪº
    0.20
    æ¸ĹéĢı
    0.20
    æģļ
    0.20
    éĴ¢åİĤ
    0.20
    çIJĨç§ij
    0.20
    -cli
    0.20
    çĪ±åĽ½
    0.20
    大åѦçĶŁ
    0.19
    éĿĴæĺ¥
    0.19
    Activations Density 0.052%

    No Known Activations