© 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. 20138
    Prev
    Next
    INDEX
    Explanations

    coastline, coast, frontage, facing

    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
    å±Ī
    -0.09
    å®¢åľº
    -0.09
    åľ¨å½ĵåľ°
    -0.09
    åľ¨äº¬
    -0.09
    åıªä¸º
    -0.09
    æ³¥
    -0.08
    å·¥ä½ľæķĪçİĩ
    -0.08
    èıħ
    -0.08
    æĥħä¾£
    -0.08
    åħ¨åĬĽä»¥
    -0.08
    POSITIVE LOGITS
    æݥ触åĪ°
    0.10
    ÅĽci
    0.10
    èĦĸåŃIJ
    0.09
    æ¿Ĵ
    0.09
    缴æİ¥
    0.09
    å¾Īéķ¿
    0.09
     trom
    0.09
    èĬ¥
    0.09
     Aure
    0.09
    Facing
    0.08
    Activations Density 0.100%

    No Known Activations