© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52349
    Prev
    Next
    INDEX
    Explanations

    cascade, avalanche

    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
    mate
    -0.10
    ession
    -0.09
    é£İæ³¢
    -0.09
    æĦł
    -0.09
    åĬ©çIJĨ
    -0.09
    æļĩ
    -0.09
     каÑĩ
    -0.09
    orno
    -0.08
    ãģĵãĤį
    -0.08
    åĨ¥
    -0.08
    POSITIVE LOGITS
    è·Į
    0.10
    æķĪæŀľ
    0.10
    ا
    0.10
    èĢĮåĩº
    0.09
    _fonts
    0.09
    è¯ĺ
    0.09
    olor
    0.09
    ingly
    0.09
    ous
    0.09
    æ½ľèĥ½
    0.09
    Activations Density 0.008%

    No Known Activations