© 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. 17678
    Prev
    Next
    INDEX
    Explanations

    recruited from

    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
    eland
    -0.11
    etas
    -0.11
    ect
    -0.09
    å°ıåŃ©åŃIJ
    -0.09
    ort
    -0.09
    çī¹æ´¾åijĺ
    -0.09
    士
    -0.09
    /***/
    -0.09
    å¸ĮæľĽéĢļè¿ĩ
    -0.09
     lẽ
    -0.08
    POSITIVE LOGITS
    åľ¨çĶŁæ´»ä¸Ń
    0.11
    èĮ«èĮ«
    0.10
    vana
    0.10
    æĿ²
    0.09
    çĶŁæ´»ä¸Ń
    0.09
    管çIJĨå±Ĥ
    0.09
    æ·Ŀ
    0.08
    åľ¨å¸Ĥåľºä¸Ĭ
    0.08
    æ´Ĺå¹²åĩĢ
    0.08
    kit
    0.08
    Activations Density 0.074%

    No Known Activations