© 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. 53519
    Prev
    Next
    INDEX
    Explanations

    systemd service files

    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
    èµ·çłģ
    -0.10
     Isles
    -0.10
    åijĨ
    -0.09
     celebrated
    -0.08
    icho
    -0.08
    burgh
    -0.08
    éķIJ
    -0.08
     stuck
    -0.08
    æĥ³è¿ĩ
    -0.08
    ä½ĵéªĮ
    -0.08
    POSITIVE LOGITS
    ìĦľë¹ĦìĬ¤
    0.09
    èĵ¼
    0.08
    客æĪ·æľįåĬ¡
    0.08
     ccp
    0.08
    ponsor
    0.08
    íħį
    0.08
    ê¶Į
    0.08
    .Service
    0.08
    ä¸Ģå¿ĥ
    0.08
    service
    0.08
    Activations Density 0.106%

    No Known Activations