© 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. 23650
    Prev
    Next
    INDEX
    Explanations

    app crashes

    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
    ãĥķãĤ©ãĥ¼
    -0.10
    误导
    -0.10
    èłķ
    -0.10
    ä¸Ģè¶Ł
    -0.10
    èĬ±çĶŁ
    -0.10
    ç¢į
    -0.10
    éĻįå¹ħ
    -0.10
    pires
    -0.09
    idget
    -0.09
    æ§Ľ
    -0.09
    POSITIVE LOGITS
     crash
    0.10
     crashes
    0.09
     Crash
    0.09
    äºĭæķħ
    0.09
    åİŁåĽł
    0.09
    arte
    0.09
    éĻĮçĶŁäºº
    0.08
    SIDE
    0.08
    ÑĮ
    0.08
    ::-
    0.08
    Activations Density 0.214%

    No Known Activations