© 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. 23611
    Prev
    Next
    INDEX
    Explanations

    benefits to

    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
    äºĨä¸Ģç³»åĪĹ
    -0.10
     tales
    -0.09
    å¾Ģä¸ĭ
    -0.09
    å¾Ĵ
    -0.09
    inia
    -0.08
     manh
    -0.08
    æīĭåĬ¿
    -0.08
    ete
    -0.08
    ety
    -0.08
    件äºĭ
    -0.08
    POSITIVE LOGITS
    ÑĢин
    0.10
    åı£æ°Ķ
    0.09
    æ®Ĩ
    0.09
    个ä½ĵ
    0.09
    ä¸įèĥ½åĨį
    0.09
     minValue
    0.09
    身ä½ĵåģ¥åº·
    0.09
     society
    0.09
    ä¸į大
    0.09
    çIJĨæĻº
    0.08
    Activations Density 0.048%

    No Known Activations