© 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. 39727
    Prev
    Next
    INDEX
    Explanations

    Florida cities and 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
    西å®ģ
    -0.10
    çĶĺèĤĥ
    -0.10
    çĶĺèĤĥçľģ
    -0.10
    峨
    -0.10
    èľĢ
    -0.10
    éĤł
    -0.10
    西èĹı
    -0.10
    èĬ±æ¤Ĵ
    -0.09
    åĮĹ京å¸Ĥ
    -0.09
    éĻĩ
    -0.09
    POSITIVE LOGITS
     Florida
    0.20
    Florida
    0.19
     Tampa
    0.19
    åľ¨æ·±åľ³
    0.18
    Miami
    0.17
     Miami
    0.16
    çĥŃ带
    0.16
    æ·±åľ³å¸Ĥ
    0.14
    æ·±åľ³
    0.14
    æµ·åįĹçľģ
    0.14
    Activations Density 0.196%

    No Known Activations