© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2220
    Prev
    Next
    INDEX
    Explanations

    derivative calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    è°ĥéħį
    -0.26
    åIJĦèĩªçļĦ
    -0.26
    åĪĨå·¥
    -0.25
    åIJĦèĩª
    -0.23
    çļĦä½ľåĵģ
    -0.23
    çļĦæ°Ķæģ¯
    -0.22
    äºĨåIJ§
    -0.22
    /packages
    -0.22
     Beverage
    -0.21
    å¤ĩ注
    -0.21
    POSITIVE LOGITS
     Kitt
    0.25
    ivia
    0.24
    èĩªå¾ĭ
    0.22
    èµ°åĩº
    0.22
    让èĩªå·±
    0.22
    Scalars
    0.22
    代è¨Ģ
    0.22
    俺
    0.22
    å¨ģ
    0.22
    Beyond
    0.22
    Activations Density 0.005%

    No Known Activations