© 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. 11692
    Prev
    Next
    INDEX
    Explanations

    negative qualifications

    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
    çķ´
    -0.23
    à¹Ħล
    -0.20
     Blaze
    -0.20
    头åıij
    -0.20
    è§ģè¯ģ
    -0.20
    å¼ĺ
    -0.20
     fle
    -0.18
    éĹ¨æ§Ľ
    -0.18
    ä½ľåĵģ
    -0.18
    åĴ³
    -0.18
    POSITIVE LOGITS
    uche
    0.21
    ä½Ĩä»į
    0.20
     Alphabet
    0.20
    ição
    0.19
     Getter
    0.19
     concess
    0.18
    çĶļèĩ³æĺ¯
    0.18
    STRU
    0.18
     dov
    0.18
     enc
    0.18
    Activations Density 0.405%

    No Known Activations