© 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. 16095
    Prev
    Next
    INDEX
    Explanations

    drag queen performances

    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
    ä¼Ļä¼´åħ³ç³»
    -0.20
    EMA
    -0.19
    getManager
    -0.18
    CMP
    -0.18
    æķŀ
    -0.18
    OfType
    -0.18
     Gutenberg
    -0.18
    èĿ½
    -0.18
    绿èī²åıijå±ķ
    -0.18
    æĶ¾æīĭ
    -0.18
    POSITIVE LOGITS
    usc
    0.20
    éĩĩçŁ¿
    0.20
    嬿
    0.19
    äºīåıĸ
    0.19
    ç®ķ
    0.19
    ape
    0.18
    èĪŀ
    0.18
    è·³èĪŀ
    0.18
    eat
    0.18
    ç¦ıåĪ©
    0.18
    Activations Density 0.004%

    No Known Activations