© 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. 12164
    Prev
    Next
    INDEX
    Explanations

    Clery Act, Data Systems, Roles of

    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
    å±ł
    -0.22
    弧
    -0.19
    BLE
    -0.19
    sWith
    -0.19
    ä¸ĬæĬ¥
    -0.19
    æľĢåIJİ
    -0.19
    ä¹ĥèĩ³
    -0.18
    èĴĻ
    -0.18
    ä»ĸå¦Ī
    -0.18
    çķ¥
    -0.18
    POSITIVE LOGITS
    ports
    0.21
    æŁŀ
    0.19
    -dist
    0.18
    åľĥ
    0.18
    _primitive
    0.18
    #line
    0.17
    å¦į
    0.17
    é¼ł
    0.17
    ÂŃs
    0.17
    Href
    0.17
    Activations Density 0.001%

    No Known Activations