© 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. 2012
    Prev
    Next
    INDEX
    Explanations

    not disclosed, meet Dr

    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
    èŀįåħ¥
    -0.23
     Clubs
    -0.23
     seldom
    -0.23
     rarely
    -0.23
    èĢĹ
    -0.23
    ustum
    -0.22
    _simps
    -0.22
    belongs
    -0.22
    çļĦæĦŁåıĹ
    -0.22
    æĻºåĬĽ
    -0.21
    POSITIVE LOGITS
    åijĬè¯īè®°èĢħ
    0.29
     specifics
    0.29
    åĵ½
    0.24
    说éģĵ
    0.23
     sagte
    0.23
    åĿ¦è¨Ģ
    0.23
    说äºĨ
    0.23
    ä¸Ģä¸Ģ
    0.22
    äºĴèģĶç½ij
    0.22
    说ä»Ģä¹Ī
    0.22
    Activations Density 0.004%

    No Known Activations