© 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. 33795
    Prev
    Next
    INDEX
    Explanations

    blank slate

    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
    å°¾
    -0.10
     Tail
    -0.10
    宵
    -0.09
    åıĭåĸĦ
    -0.08
    licer
    -0.08
    åĴĮæľįåĬ¡
    -0.08
    .tail
    -0.08
    nameof
    -0.08
    coon
    -0.08
    	UI
    -0.08
    POSITIVE LOGITS
    空çĻ½
    0.21
     blank
    0.19
    blank
    0.15
     slate
    0.14
     fresh
    0.14
    ä¸Ģçīĩ
    0.14
     Blank
    0.14
    å¹²åĩĢ
    0.13
    Blank
    0.13
    为空
    0.13
    Activations Density 0.097%

    No Known Activations