© 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. 27197
    Prev
    Next
    INDEX
    Explanations

    reliable services and goods

    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
    åIJĪçIJĨæĢ§
    -0.10
    ç¢Į
    -0.09
    æ£Ģå¯Łå®ĺ
    -0.09
    åijĹ
    -0.09
    ÕŃ
    -0.09
    æĻı
    -0.09
    è¾ķ
    -0.08
    人æĸĩ
    -0.08
    leri
    -0.08
    çĸ£
    -0.08
    POSITIVE LOGITS
    åı¯éĿł
    0.20
    åı¯éĿłçļĦ
    0.19
     reliable
    0.14
     Reliable
    0.13
    åı¯éĿłæĢ§
    0.13
    åı¯ä¿¡
    0.12
     dependable
    0.12
    稳å®ļçļĦ
    0.11
     trustworthy
    0.11
    oda
    0.10
    Activations Density 0.021%

    No Known Activations