© 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. 14709
    Prev
    Next
    INDEX
    Explanations

    do it yourself

    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
    éĴ²
    -0.20
    è¾ħ
    -0.20
     Arist
    -0.20
    abin
    -0.20
    æ¯ĭ
    -0.19
    ä¸İåħ¶ä»ĸ
    -0.18
    åĩºä¼ļ
    -0.18
    Unchecked
    -0.18
     PRI
    -0.18
    çľĭä¸įè§ģ
    -0.18
    POSITIVE LOGITS
     DIY
    0.41
    èĩªè¡Į
    0.39
    èĩªåѦ
    0.33
    DI
    0.31
    ä¸ļä½Ļ
    0.30
     ÑģамоÑģÑĤоÑıÑĤелÑĮно
    0.30
    èĩªåĬ©
    0.29
     ÑģамоÑģÑĤоÑı
    0.29
    亲èĩª
    0.29
    æľ¬äºº
    0.29
    Activations Density 0.079%

    No Known Activations