© 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. 15526
    Prev
    Next
    INDEX
    Explanations

    Parrish, Callahan, Vonleh, Cattermole, Sherrod, Friedl, Eveland, Gostisbehere, Rea

    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
    ocracy
    -0.22
    ologist
    -0.22
    conomy
    -0.20
    /h
    -0.19
    åĪ»
    -0.19
    åı¨
    -0.19
     Alta
    -0.18
    -images
    -0.18
    æ³ķ人
    -0.18
     news
    -0.18
    POSITIVE LOGITS
     pornô
    0.22
    åIJİåį«
    0.21
     ÑģÑĤанд
    0.20
    åĮĸçŁ³
    0.20
    æĤłæĤł
    0.20
    åĽ¢ä¼Ļ
    0.19
    éĴİ
    0.19
    вел
    0.19
    模çī¹
    0.19
    ä¸Ģ带
    0.19
    Activations Density 0.032%

    No Known Activations