© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19755
    Prev
    Next
    INDEX
    Explanations

    things to do and see

    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
    éªĭ
    -0.09
    å¸ĮæľĽéĢļè¿ĩ
    -0.09
    çĻ»
    -0.09
    ulet
    -0.09
    åıijå±ķæł¼å±Ģ
    -0.08
    éĶ¦æłĩèµĽ
    -0.08
    衽
    -0.08
    åĿļæŀľ
    -0.08
    æĽľ
    -0.08
    缴æĴŃéĹ´
    -0.08
    POSITIVE LOGITS
     nearby
    0.10
    åij¨è¾¹
    0.10
    éĻĦè¿ij
    0.10
    åij¨åĽ´
    0.10
     attractions
    0.09
    çī©ä»·
    0.09
     sights
    0.09
    èģļéĽĨ
    0.09
    æĸĩæĺĮ
    0.09
     Attr
    0.08
    Activations Density 0.103%

    No Known Activations