© 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. 2852
    Prev
    Next
    INDEX
    Explanations

    don't mind

    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
    ye
    -0.25
     MRI
    -0.23
    usan
    -0.23
     MIS
    -0.22
    ndl
    -0.22
     CES
    -0.21
    during
    -0.21
    ALAR
    -0.21
    åı¯éĿłæĢ§
    -0.21
    éĩįçĤ¹åħ³æ³¨
    -0.21
    POSITIVE LOGITS
     admitting
    0.29
    æİ¥åıĹ
    0.27
    ä¸įåħ¬å¹³
    0.25
     accepting
    0.25
     accept
    0.24
    ä¸Ģå®ļç¨ĭ度
    0.24
     acept
    0.24
    izedName
    0.23
     nudity
    0.23
    ä¸įåľ¨ä¹İ
    0.23
    Activations Density 0.018%

    No Known Activations