© 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. 12792
    Prev
    Next
    INDEX
    Explanations

    Firefox browser

    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
    éŀĺ
    -0.22
    åķ¬
    -0.21
    jos
    -0.19
    ivos
    -0.19
    èľļ
    -0.19
    çķ¹
    -0.18
    æĦŁ
    -0.18
    èģĴ
    -0.18
    alah
    -0.17
    ÑĪки
    -0.17
    POSITIVE LOGITS
    çīĪ
    0.21
    好åIJĹ
    0.20
    -only
    0.19
    ulg
    0.19
    çĻ¾è´§
    0.18
    è¿ĻäºĽéĹ®é¢ĺ
    0.18
    åħ¥æĪ·
    0.18
    çĭ¬æľīçļĦ
    0.18
    rab
    0.18
    éĻ¤æѤä¹ĭå¤ĸ
    0.17
    Activations Density 0.007%

    No Known Activations