© 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. 2947
    Prev
    Next
    INDEX
    Explanations

    describing physical characteristics

    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
    ä¸ĢåĽŀäºĭ
    -0.23
    ä¼Ł
    -0.22
    æľ¯
    -0.22
    ç«ŀèµĽ
    -0.22
    aname
    -0.22
    aje
    -0.21
    èĤ¯å®ļæĺ¯
    -0.21
    tri
    -0.21
    ftime
    -0.21
    çķª
    -0.21
    POSITIVE LOGITS
    /A
    0.24
    uty
    0.23
    åŀĭ
    0.23
    _plate
    0.23
    åĢ¾åIJij
    0.23
    ATED
    0.23
     aggravated
    0.23
    itis
    0.22
    /w
    0.22
    ulent
    0.22
    Activations Density 0.007%

    No Known Activations