© 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. 16251
    Prev
    Next
    INDEX
    Explanations

    label followed by colon

    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
     ÐIJлекÑģан
    -0.34
    à¹Ģà¸Ĺà¸Ħà¹Ĥà¸Ļ
    -0.31
     ÐŁÐ¾Ñĩем
    -0.30
    à¹Ĥรà¸ĩà¸ŀยา
    -0.29
    à¸Ħà¸ĵะà¸ģรรม
    -0.28
    à¸Ńำà¸Ļวยà¸Ħวาม
    -0.28
     PaÅĦstwo
    -0.26
    èĢĮä¸įæĺ¯
    -0.25
    ÑĩÑĢежден
    -0.25
    à¸Ħะà¹ģà¸Ļ
    -0.25
    POSITIVE LOGITS
    :
    0.40
    ï¼ļ
    0.29
    :↵
    0.24
    â¬Ĭ
    0.22
    (optional
    0.21
    çķ¥
    0.20
    :**
    0.20
    ::
    0.19
    áµĪ
    0.19
    :;↵
    0.19
    Activations Density 0.240%

    No Known Activations