© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 14914
    Prev
    Next
    INDEX
    Explanations

    guide or roadmap

    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
     Consort
    -0.20
    åĪ°è´¦
    -0.20
    nal
    -0.19
    wine
    -0.19
    auen
    -0.19
    æģĤ
    -0.19
    éĴ¤
    -0.18
    isters
    -0.18
    主管
    -0.18
    é¦ĸä½į
    -0.18
    POSITIVE LOGITS
    ä¾Ľå¤§å®¶
    0.30
    æķ´çIJĨ
    0.27
    大åħ¨
    0.24
    让大家
    0.24
    å¸ĮæľĽå¤§å®¶
    0.23
    åħ¨éĿ¢
    0.23
    干货
    0.23
     handy
    0.22
    å¸ĮæľĽèĥ½
    0.22
    æµģæ°´
    0.21
    Activations Density 0.172%

    No Known Activations