© 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. 4847
    Prev
    Next
    INDEX
    Explanations

    use or absence

    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
    ÃĤN
    -0.08
     drift
    -0.08
    atives
    -0.08
    chie
    -0.08
    çļĦè¦ģæ±Ĥ
    -0.08
    entr
    -0.08
    otte
    -0.08
    .vs
    -0.07
    人人éĥ½
    -0.07
    人人
    -0.07
    POSITIVE LOGITS
    åĴĮåıijå±ķ
    0.13
    ä¸İåıijå±ķ
    0.11
    ä¸İåIJ¦
    0.10
    楼ä¸Ĭ
    0.10
    ãģĤãĤĮ
    0.10
    æīĢåľ¨
    0.09
    ä¹ŁæĪIJ为
    0.09
    åıĬåħ¶
    0.09
    åľ°ä¸Ĭ
    0.09
    ä¸įåłª
    0.09
    Activations Density 0.200%

    No Known Activations