© 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. 3268
    Prev
    Next
    INDEX
    Explanations

    following GNU or function

    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
    æĦŁåĪ°
    -0.09
    çĶĺ
    -0.09
    æĺ¾å¾Ĺ
    -0.08
    æĢİä¹ĪåĬŀ
    -0.08
    æī©
    -0.08
    æĪijè§īå¾Ĺ
    -0.08
    .getObject
    -0.08
    éļ¾éģĵ
    -0.08
     Downs
    -0.08
     Orr
    -0.08
    POSITIVE LOGITS
    æľīå¤ļä¹Ī
    0.11
     rằng
    0.09
    æľīå¤ļ
    0.08
    stract
    0.08
    utations
    0.08
    æĺ¯æĪijçļĦ
    0.08
    ä¼ļåĩºçİ°
    0.08
     allegiance
    0.08
    åıijçĶŁäºĨ
    0.08
    æĺ¯éŁ©åĽ½
    0.08
    Activations Density 0.257%

    No Known Activations