© 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. 2062
    Prev
    Next
    INDEX
    Explanations

    unusual weather seasons

    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
    çĽ²
    -0.35
     blind
    -0.27
    å±Ĥ级
    -0.25
    æ®ī
    -0.25
    ä¸Ģç«Ļ
    -0.24
     bail
    -0.24
    º«
    -0.24
     permanent
    -0.24
     Crus
    -0.24
    认
    -0.24
    POSITIVE LOGITS
     unusually
    0.44
     unusual
    0.38
     unprecedented
    0.36
     drought
    0.35
    æ°ĶåĢĻ
    0.34
    è¿Ļä¸Ģå¹´
    0.30
    ä»Ĭå¹´
    0.30
     anomal
    0.30
    alendar
    0.30
     rainfall
    0.29
    Activations Density 0.034%

    No Known Activations