© 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. 14514
    Prev
    Next
    INDEX
    Explanations

    College followed by location

    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
     ÐIJлекÑģан
    -0.21
     ÐŁÐ¾Ñĩем
    -0.20
     даж
    -0.19
     моÑīн
    -0.18
    æĢĶ
    -0.18
    ä¸Ģç±»
    -0.18
    ä¸įèī¯ä¿¡æģ¯
    -0.18
     ÐĶм
    -0.17
    iko
    -0.17
    å¸Ī
    -0.17
    POSITIVE LOGITS
    hung
    0.19
    éĨį
    0.18
    bindValue
    0.18
    åīįæıIJ
    0.17
    ç»´å°Ķ
    0.17
    ä¸įè¦ģåĨį
    0.17
     knight
    0.17
    é¤IJåħ·
    0.17
    _PG
    0.17
    禧
    0.17
    Activations Density 0.010%

    No Known Activations