© 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. 17572
    Prev
    Next
    INDEX
    Explanations

    offers services and products

    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
     itself
    -0.09
    计
    -0.08
    ought
    -0.08
    åı¦ä¸Ģæĸ¹éĿ¢
    -0.08
    åı¦ä¸Ģè¾¹
    -0.08
    zen
    -0.08
    çĬģ
    -0.08
    lick
    -0.08
    llib
    -0.08
     Ùħض
    -0.08
    POSITIVE LOGITS
    _SLEEP
    0.10
    embro
    0.10
     Slee
    0.09
    ä¸įæŃ¢
    0.09
    åĪº
    0.09
    æŀĭ
    0.09
     UIS
    0.09
    棹
    0.09
    çĭ¬ä¸ĢæĹłäºĮ
    0.09
    artner
    0.09
    Activations Density 0.065%

    No Known Activations