© 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. 62432
    Prev
    Next
    INDEX
    Explanations

    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
    èĶĵ
    -0.10
    èĦĸ
    -0.10
    tics
    -0.09
    semb
    -0.09
    åį§
    -0.09
    æĤł
    -0.08
    moid
    -0.08
    ãĥ¬ãĥ³
    -0.08
    ç¼ĵç¼ĵ
    -0.08
    تØŃر
    -0.08
    POSITIVE LOGITS
    é£İ鼨
    0.19
    é£İ
    0.16
    é£İæļ´
    0.15
     wind
    0.14
    風
    0.13
    åı°é£İ
    0.13
    å¤§éĽ¨
    0.13
     winds
    0.13
    æļ´éĽ¨
    0.13
    æĬĹ
    0.13
    Activations Density 0.095%

    No Known Activations