© 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. 11635
    Prev
    Next
    INDEX
    Explanations

    stories, theories, belief

    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
     пÑĢиÑıÑĤн
    -0.28
    sÅĤaw
    -0.27
    mówi
    -0.26
    ÅŁeh
    -0.26
    à¤ĭ
    -0.26
     salopes
    -0.25
     bezpo
    -0.25
    chestra
    -0.25
    è°¢éŁµ
    -0.25
     ÐIJлекÑģан
    -0.25
    POSITIVE LOGITS
     belief
    0.28
     paranormal
    0.27
    ç§ijåŃ¦å®¶
    0.27
     scientific
    0.27
    ç¥ŀç§ĺ
    0.26
    è¿Ļç±»
    0.25
    æ°ijéĹ´
    0.25
    èĢĥè¯ģ
    0.25
    ç§ijåѦçłĶ究
    0.25
    æѤ类
    0.25
    Activations Density 0.096%

    No Known Activations