© 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. 16438
    Prev
    Next
    INDEX
    Explanations

    enumerated lists separated by commas

    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
    -0.40
     ÐŁÐ¾Ñĩем
    -0.33
     ÐĶмиÑĤÑĢ
    -0.27
    à¸Ħà¸ĵะà¸ģรรม
    -0.27
     заÑĢегиÑģÑĤ
    -0.26
     à¹Ģมษ
    -0.25
     à¸ŀฤษ
    -0.25
    à¹Ĥรà¸ĩà¸ŀยา
    -0.25
    ÑĩÑĢежден
    -0.24
     มà¸ģร
    -0.24
    POSITIVE LOGITS
     etc
    0.27
     salopes
    0.23
    iéndo
    0.20
    ฯ
    0.19
    oreferrer
    0.19
    âĤĮ
    0.19
    ãİĽ
    0.19
     milfs
    0.19
    'gc
    0.19
    ᶣ
    0.18
    Activations Density 0.212%

    No Known Activations