© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20356
    Prev
    Next
    INDEX
    Explanations

    winter holiday locations

    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
    æ·±å¤ľ
    -0.09
     Huff
    -0.09
    çĿ¢
    -0.09
    æĤĦ
    -0.08
    éĺľ
    -0.08
    éĵ°
    -0.08
    åĬ±
    -0.08
    åݲ
    -0.08
    éĥ§
    -0.08
    åĿĬ
    -0.08
    POSITIVE LOGITS
     tropical
    0.12
     sun
    0.12
    éĺ³åħī
    0.12
    çĥŃ带
    0.11
    温
    0.11
    æ°ĶåĢĻ
    0.10
    æµ·åįĹ
    0.10
    度åģĩ
    0.10
    åįĹå±±
    0.10
     Florida
    0.10
    Activations Density 0.157%

    No Known Activations