© 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. 34756
    Prev
    Next
    INDEX
    Explanations

    highway, route, interstate, road

    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
    çĶ²çĬ¶
    -0.10
    æ½®
    -0.09
    箪
    -0.09
    azy
    -0.09
    åħ¬åħ±åľºæīĢ
    -0.09
    æĽ³
    -0.09
    éĩıåĮĸ
    -0.09
    orra
    -0.09
    å¤ļè¾¾
    -0.09
    (strict
    -0.09
    POSITIVE LOGITS
    é«ĺéĢŁåħ¬è·¯
    0.10
    çIJ¥
    0.10
     Gran
    0.09
    é«ĺéĢŁ
    0.09
     highway
    0.09
    èĥŃ
    0.08
    åħ¬è·¯
    0.08
    è¿ĻæĿ¡
    0.08
    ç¥Ŀ
    0.08
     Highway
    0.08
    Activations Density 0.287%

    No Known Activations