© 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. 39131
    Prev
    Next
    INDEX
    Explanations

    past or by

    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
    åĿ¨
    -0.11
    ä»ħ次äºİ
    -0.09
    ç¯ĵ
    -0.09
    å©·
    -0.09
    èĥ½åģļåĪ°
    -0.09
    姣
    -0.09
    æĢİä¹Ī说
    -0.09
    丧失
    -0.09
    讼
    -0.09
    åıªè¦ģä½ł
    -0.09
    POSITIVE LOGITS
    eka
    0.11
    fare
    0.10
    è¿ĩçļĦ
    0.09
    è¿ĩæĿ¥
    0.09
    主å¸Ń
    0.09
    ä¸Ģéģį
    0.08
     bluff
    0.08
    ibal
    0.08
     ÑĢа
    0.08
     Passing
    0.08
    Activations Density 0.058%

    No Known Activations