© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 26525
    Prev
    Next
    INDEX
    Explanations

    extreme weather conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    侪
    -0.09
     Din
    -0.09
     Demonstr
    -0.08
    çªł
    -0.08
    å®Įæķ´
    -0.08
     Dynamics
    -0.08
    å®īåħ¨äºĭæķħ
    -0.08
    å¿ĥ仪
    -0.08
    羶
    -0.08
    èĭĹ
    -0.08
    POSITIVE LOGITS
    å¯ĴåĨ·
    0.19
    æ²Ļæ¼ł
    0.17
    æģ¶åĬ£
    0.17
    天æ°Ķ
    0.16
    ä½İ温
    0.16
    å¯Ĵ
    0.15
    é«ĺ温
    0.14
    çĤİçĥŃ
    0.14
     weather
    0.14
    åĨ»
    0.14
    Activations Density 0.183%

    No Known Activations