© 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. 15460
    Prev
    Next
    INDEX
    Explanations

    emotional states and outcomes

    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
    çīĻ
    -0.23
    çķ¥
    -0.21
    çĻ»
    -0.21
    åIJĦåįķä½į
    -0.21
    ifestyles
    -0.20
    å¾Ĵ
    -0.20
    åĽĽæĸ¹
    -0.19
    ÑĩÑĢежден
    -0.19
    æĪIJåĵģ
    -0.19
    ä¸ĩéĩĮ
    -0.19
    POSITIVE LOGITS
    æĥħæĦŁ
    0.19
     burden
    0.19
     ÑģоÑģÑĤоÑıние
    0.19
    éĴ¤
    0.18
    åģİ
    0.18
     and
    0.18
    æģ¶åĮĸ
    0.18
     sensitivity
    0.17
    鸡汤
    0.17
    æĢ«
    0.17
    Activations Density 0.018%

    No Known Activations