© 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. 17222
    Prev
    Next
    INDEX
    Explanations

    age or adult requirements

    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
    被æīĵ
    -0.10
    ä¸į失
    -0.10
    åıĬæŶ
    -0.08
    æ·¡æ·¡çļĦ
    -0.08
    å§IJ
    -0.08
    åŁİéĩĮ
    -0.08
    å·´æĸ¯
    -0.08
    Observ
    -0.08
    å½¢
    -0.08
    .vaadin
    -0.08
    POSITIVE LOGITS
    å¹´é¾Ħ
    0.11
    à¸Ńาย
    0.10
    èĮĦ
    0.10
    éĺģ
    0.10
    æļĹ示
    0.09
    æķ¬è¯·
    0.09
    idden
    0.09
    åľ°çIJĨä½įç½®
    0.09
    çĨŁçŁ¥
    0.09
    éĺ¶å±Ĥ
    0.08
    Activations Density 0.023%

    No Known Activations