© 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. 47806
    Prev
    Next
    INDEX
    Explanations

    wind 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
    éĢłè¡Ģ
    -0.10
    _ATTRIB
    -0.09
     Countdown
    -0.09
    åħīçݯ
    -0.09
    æŃ£è§Ħ
    -0.09
     AUTHORS
    -0.09
    äºĮç»´çłģ
    -0.08
    åĬłåħ¥äºĨ
    -0.08
    associ
    -0.08
    æ·ŀ
    -0.08
    POSITIVE LOGITS
     winds
    0.12
    é£İ
    0.12
    wind
    0.12
     wind
    0.11
    é£İæľº
    0.10
    åĪĺæµ·
    0.10
     conditions
    0.10
    天æ°Ķ
    0.10
    風
    0.09
    é£İçĶµ
    0.09
    Activations Density 0.071%

    No Known Activations