© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19866
    Prev
    Next
    INDEX
    Explanations

    state and laws

    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
    åģı
    -0.09
    åIJijå¾Ģ
    -0.09
    è¥Ħ
    -0.09
     Sunder
    -0.09
    人çĶŁçļĦ
    -0.09
    å±±åĮº
    -0.09
    .obtain
    -0.08
    ä¿Ŀ
    -0.08
    missions
    -0.08
    ridge
    -0.08
    POSITIVE LOGITS
     hood
    0.10
    åĴĮæĬĢæľ¯
    0.10
    åıijåħī
    0.09
     autonomous
    0.09
     individually
    0.08
    vro
    0.08
    èĩªä¸»
    0.08
    æ±°
    0.08
    åıĹåĪ°å½±åĵį
    0.08
    orts
    0.08
    Activations Density 0.039%

    No Known Activations