© 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. 38238
    Prev
    Next
    INDEX
    Explanations

    ends with ia/ine/ino/in

    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
    è¿ŀéĶģ
    -0.09
    ghi
    -0.09
    ç½®
    -0.09
    ä»Ķ
    -0.09
    æľ«ç«¯
    -0.08
    ä¼ŀ
    -0.08
    çĤ¹äºĨ
    -0.08
    .qq
    -0.08
    /rss
    -0.08
    åı¯çĪ±çļĦ
    -0.08
    POSITIVE LOGITS
    Unnamed
    0.10
    oki
    0.10
    æĺĤè´µ
    0.09
    æIJħ
    0.09
    åīįåIJİ
    0.09
    èĢĹ
    0.08
    ç§ī
    0.08
    è°Ĩ
    0.08
    atted
    0.08
    igma
    0.08
    Activations Density 0.240%

    No Known Activations