© 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. 15802
    Prev
    Next
    INDEX
    Explanations

    by country, size, age, body

    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
    ä¹ĭæĺŁ
    -0.19
     Durant
    -0.18
    _utilities
    -0.18
     kå
    -0.18
    Regressor
    -0.18
    çļĦä¸ĢåĪĩ
    -0.18
    _lit
    -0.17
    _logits
    -0.17
    tokenizer
    -0.17
    æ¯ı个人éĥ½
    -0.17
    POSITIVE LOGITS
    æŶéĹ´åĴĮ
    0.32
     size
    0.29
    åħ¶æīĢ
    0.29
    åĽ½ç±į
    0.26
    å¹´é¾Ħ
    0.26
    æŶéĹ´æ®µ
    0.25
    身份
    0.25
     location
    0.25
     age
    0.25
    åıijå±ķéĺ¶æ®µ
    0.24
    Activations Density 0.113%

    No Known Activations