© 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. 14610
    Prev
    Next
    INDEX
    Explanations

    flora and fauna

    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
    å¾Īå¤ļäºĭæĥħ
    -0.19
    raud
    -0.19
    åIJĦè¡ĮåIJĦ
    -0.19
    моÑĢ
    -0.19
    peria
    -0.19
    ÑħваÑĤ
    -0.19
    失败
    -0.18
     Geile
    -0.18
    æŁ
    -0.18
    åĪ°æľĢåIJİ
    -0.18
    POSITIVE LOGITS
    åIJįå½ķ
    0.26
    è¯ĨåĪ«
    0.22
    ç§įç±»
    0.22
     richness
    0.21
    GY
    0.20
    ç½ijè´Ń
    0.20
    çŁ¥è¯Ĩ
    0.20
    åݿ级
    0.20
    åħ¨åİ¿
    0.20
    èĹĵ
    0.19
    Activations Density 0.047%

    No Known Activations