© 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. 39932
    Prev
    Next
    INDEX
    Explanations

    Memory complaints

    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
    æı¡ä½ı
    -0.09
    å¾ĭ
    -0.09
    çľŃ
    -0.09
    嵯
    -0.09
    辫
    -0.09
    åĩºéģĵ
    -0.09
    çIJ´
    -0.09
    çŃĴ
    -0.09
    æľĶ
    -0.08
    æ°¡
    -0.08
    POSITIVE LOGITS
    æľ¬æľŁ
    0.09
    æĪŁ
    0.08
    çĽij管éĥ¨éŨ
    0.08
    -contained
    0.08
    iko
    0.08
    ä¸įä¸Ĭ
    0.08
    ç²ī
    0.08
    iegel
    0.08
    ä¸Ģå°ı
    0.08
     Mall
    0.08
    Activations Density 0.010%

    No Known Activations