© 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. 16535
    Prev
    Next
    INDEX
    Explanations

    URLs with 'thread' or 'bug'

    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
    ä»ĬçĶŁ
    -0.23
    ÑĥÑĢÑģ
    -0.19
    åĩºç¤º
    -0.19
    çĻ»è®°
    -0.19
    æĮĤåı·
    -0.18
    ocale
    -0.18
    SOLE
    -0.17
    íĿ¬
    -0.17
    iras
    -0.17
    cept
    -0.17
    POSITIVE LOGITS
    çĤ¹å¤ļ
    0.20
    ä¿Ĺè¯Ŀ说
    0.19
    çľ¼åħī
    0.19
    locks
    0.18
    ä¸Ńåħ³
    0.18
    ük
    0.18
    ä¼ĹæīĢ
    0.18
    çİij
    0.17
     Slam
    0.17
    athi
    0.17
    Activations Density 0.012%

    No Known Activations