© 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. 49932
    Prev
    Next
    INDEX
    Explanations

    things happen or change

    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
    ÑģÑĮ
    -0.08
     оÑģнове
    -0.08
    åĺ´éĩĮ
    -0.08
     shark
    -0.08
    èĢĮä¸į
    -0.08
     tercer
    -0.08
    åĥ»
    -0.08
     Somebody
    -0.08
    бÑĥ
    -0.08
    apon
    -0.07
    POSITIVE LOGITS
    åľ¨å¹¿å·ŀ
    0.11
    ä¹ŁåĽłæѤ
    0.10
    lement
    0.10
    åľ¨æ·±åľ³
    0.09
    åľ¨å®¶
    0.09
    dit
    0.09
    åľ¨äº¬
    0.09
    津贴
    0.09
    iej
    0.09
    亦
    0.09
    Activations Density 0.023%

    No Known Activations