© 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. 2518
    Prev
    Next
    INDEX
    Explanations

    Street names or addresses

    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
    çĽĨåľ°
    -0.10
    åºĶèģĺ
    -0.10
    rieb
    -0.08
    gable
    -0.08
    ç¼ĸåĪ¶
    -0.08
    ãģķãģ¾
    -0.08
    æīĵæŃ»
    -0.08
    ç´¯
    -0.08
    èĩĢ
    -0.08
    çľ¼åīį
    -0.08
    POSITIVE LOGITS
    è±ģ
    0.11
    æ©¡
    0.09
    æ¶Ĥ
    0.09
    å¾Īéķ¿
    0.08
     TAM
    0.08
    çīĪæĿĥæīĢæľī
    0.08
    åĿİåĿ·
    0.08
    ameda
    0.08
    jsonp
    0.08
    uctions
    0.08
    Activations Density 0.082%

    No Known Activations