© 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. 14172
    Prev
    Next
    INDEX
    Explanations

    hyacinths, daisy, ray, bulbs

    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
    æĻĴ
    -0.23
    å°Ĩèĩªå·±çļĦ
    -0.23
    éĺ²æĻĴ
    -0.21
    aval
    -0.19
    æŀ¯
    -0.19
    æ¯Ľå·¾
    -0.19
     ration
    -0.19
    æĻ¾
    -0.19
    ufen
    -0.19
    æĬ¹
    -0.19
    POSITIVE LOGITS
    æĿŁ
    0.20
     ÑįлекÑĤÑĢо
    0.19
    骧
    0.18
    å°Ĭ严
    0.18
    çŃ®
    0.18
     bulbs
    0.18
    ÑģÑĤÑĢой
    0.18
    libs
    0.18
    vecs
    0.18
     straight
    0.17
    Activations Density 0.010%

    No Known Activations