© 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. 14496
    Prev
    Next
    INDEX
    Explanations

    song titles

    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
    æĿµ
    -0.23
    屯
    -0.22
    æį®æѤ
    -0.22
    avage
    -0.21
    unities
    -0.21
    ients
    -0.20
    åĩłçĻ¾
    -0.20
    itoris
    -0.19
    åĨĪ
    -0.19
    æİĸ
    -0.19
    POSITIVE LOGITS
    èĩ´æķ¬
    0.23
    æĹ¢æľī
    0.22
    ç»ĵæĿŁåIJİ
    0.21
    æŃ£éĿ¢
    0.20
    æĬķå½±
    0.20
    วà¸ģ
    0.20
    尤为
    0.20
    主é¢ĺ
    0.20
     sampled
    0.19
    çģµæĦŁ
    0.18
    Activations Density 0.028%

    No Known Activations