© 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. 32469
    Prev
    Next
    INDEX
    Explanations

    campaigning for services or missions

    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
    ä¸ºæľŁ
    -0.08
    æĭĽåķĨå¼ķèµĦ
    -0.08
    UFF
    -0.08
    ç»ĻåĬĽ
    -0.08
    ä¸įä¸ĭ
    -0.08
    åİ¿æĶ¿åºľ
    -0.08
    çIJ¦
    -0.08
     Äijua
    -0.08
    å¼ĢåıijåķĨ
    -0.08
    弯
    -0.08
    POSITIVE LOGITS
    åĪĨæĶ¯æľºæŀĦ
    0.11
    ä¸ĩåįĥ
    0.10
    çĹĪ
    0.10
    åĪĨæĶ¯
    0.09
    âĺħâĺħ
    0.09
    æ¶ĤæĬ¹
    0.09
    åĭ¾
    0.09
    Äĥm
    0.09
    è½²
    0.09
    æĸ¥
    0.08
    Activations Density 0.076%

    No Known Activations