© 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. 13629
    Prev
    Next
    INDEX
    Explanations

    sexual advances and love

    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
    顶å±Ĥ
    -0.22
    åIJĪæ³ķ
    -0.20
    æĴ¼
    -0.19
    born
    -0.19
    足以
    -0.19
    æĩĴå¾Ĺ
    -0.19
    æ·¡å®ļ
    -0.19
    åĮĨåĮĨ
    -0.18
    è¾ī
    -0.18
    绣çŃ¹æİ¨è¿Ľ
    -0.18
    POSITIVE LOGITS
    æľŁå¾ħ
    0.25
    主åĬ¨
    0.23
    æľŁæľĽ
    0.23
    æĥ³
    0.20
    coc
    0.20
    æĥ³å¿µ
    0.20
    èµł
    0.20
     CALL
    0.19
    æľŁçĽ¼
    0.19
    èĩªæĪij
    0.19
    Activations Density 0.109%

    No Known Activations