© 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. 16042
    Prev
    Next
    INDEX
    Explanations

    gun parts and accessories

    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
    _LA
    -0.20
    ancestor
    -0.19
    å³°
    -0.19
     MIX
    -0.19
    /lg
    -0.19
    çĿĽ
    -0.19
    容åĻ¨
    -0.19
    -catching
    -0.19
     Hann
    -0.18
     catching
    -0.18
    POSITIVE LOGITS
    ulen
    0.21
    æľ¨è´¨
    0.21
    ä¿ĿåĪ©
    0.19
    åĪĨæľŁ
    0.18
    -stats
    0.18
     gá»Ĺ
    0.18
    书æ³ķ
    0.18
    æݧåĪ¶ç³»ç»Ł
    0.18
    ä¸Ģ个æľĪ
    0.18
     Persons
    0.18
    Activations Density 0.007%

    No Known Activations