© 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. 18252
    Prev
    Next
    INDEX
    Explanations

    gimmick, flashy, cool, sells

    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
    çĺ³
    -0.09
     MyApp
    -0.09
    ä»ĩ
    -0.08
    éĩijåŃĹ
    -0.08
    iens
    -0.08
     Dra
    -0.08
    åĿļå®ŀçļĦ
    -0.08
     dra
    -0.08
     trespass
    -0.08
    ä¹³
    -0.08
    POSITIVE LOGITS
    迷人
    0.10
    åıĪèĥ½
    0.09
    èī³
    0.09
    çł´åĿı
    0.09
    弯
    0.09
    éĹªè¿ĩ
    0.09
    æłĩçļĦ
    0.09
    èĪŁ
    0.09
    æľĢ容æĺĵ
    0.09
    éĺ¶æ®µ
    0.08
    Activations Density 0.031%

    No Known Activations