© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15153
    Prev
    Next
    INDEX
    Explanations

    Equal Opportunity Employer

    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
    çıł
    -0.25
    å´§
    -0.21
    è¿ĻåĿĹ
    -0.21
     buggy
    -0.20
     camel
    -0.19
     justification
    -0.19
    gef
    -0.18
    camel
    -0.18
    æŃ£å¼ıåIJ¯åĬ¨
    -0.18
     inf
    -0.18
    POSITIVE LOGITS
    æĺ¯ä¸Ģ家
    0.21
    æĶ¾å¼Ģ
    0.20
    èĩªçĶ±
    0.18
    sez
    0.18
    夤
    0.18
    ç»ıèIJ¥èĢħ
    0.18
    PropertyParams
    0.18
    lander
    0.17
    ä»·
    0.17
    ç§ģä¸ĭ
    0.17
    Activations Density 0.003%

    No Known Activations