© 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. 2972
    Prev
    Next
    INDEX
    Explanations

    thank you for

    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
    _reload
    -0.25
    ?q
    -0.25
    FPS
    -0.25
    æ¯Ķå¦Ĥ
    -0.22
    åħ¨æĺ¯
    -0.22
    ä½łåºĶ该
    -0.22
    hell
    -0.21
    depends
    -0.21
     rol
    -0.21
    æ¯Ķå¦Ĥ说
    -0.20
    POSITIVE LOGITS
    !.
    0.23
    nets
    0.23
    å¦ĤæѤ
    0.22
    à¸Ļะà¸Ħะ
    0.22
     вним
    0.22
    ï¼ģ
    0.21
    æĤ¨çļĦåŃ©åŃIJ
    0.21
     Ling
    0.21
     inquire
    0.21
    posix
    0.21
    Activations Density 0.025%

    No Known Activations