© 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. 38810
    Prev
    Next
    INDEX
    Explanations

    popularity and fashion trends

    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
    æľ¬ç½ij
    -0.10
    èĪįä¸įå¾Ĺ
    -0.10
    å¥īçĮ®
    -0.09
    æģ¶åĬ£
    -0.09
    æ³Į
    -0.08
    åĿļå®ļä¸į
    -0.08
    stick
    -0.08
    -contrib
    -0.08
    å£ģåŀĴ
    -0.08
    egl
    -0.08
    POSITIVE LOGITS
     popularity
    0.16
    çĥŃéŨ
    0.13
     popular
    0.13
    åıĹ欢è¿İ
    0.13
    çĥŃ度
    0.13
    人æ°Ķ
    0.12
    ä¸ĢæŶ
    0.12
    è¡°
    0.12
     попÑĥлÑıÑĢ
    0.12
    æµģè¡Į
    0.11
    Activations Density 0.105%

    No Known Activations