© 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. 2699
    Prev
    Next
    INDEX
    Explanations

    sixth broadcast season

    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
     meetup
    -0.10
     ÑģовеÑĢ
    -0.09
     Petr
    -0.09
    çĥŃéĶĢ
    -0.09
    å¾ĴæŃ¥
    -0.09
    çIJĨæĻº
    -0.09
    æľĭ
    -0.09
    CRM
    -0.09
     CRA
    -0.08
    Tesla
    -0.08
    POSITIVE LOGITS
    æĴŃåĩº
    0.16
    è§Ĥä¼Ĺ
    0.14
    èĬĤ缮
    0.14
    广çĶµ
    0.13
     viewers
    0.11
    çľĭçĶµè§Ĩ
    0.11
    çĶµè§Ĩæľº
    0.11
    çĶµè§Ĩ
    0.11
    viewer
    0.11
    åıĹä¼Ĺ
    0.11
    Activations Density 0.288%

    No Known Activations