© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9035
    Prev
    Next
    INDEX
    Explanations

    history of

    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
    èĩªå¦Ĥ
    -0.11
    halb
    -0.09
    oni
    -0.09
    èĩ¾
    -0.09
    æĪĸå¤ļ
    -0.09
    ../../../
    -0.09
    ä¸Ģæīĭ
    -0.08
    ãģ£ãģĵ
    -0.08
    æĹ¥è®°
    -0.08
    hints
    -0.08
    POSITIVE LOGITS
    åŃ¦å®¶
    0.14
    anded
    0.11
    æĤłä¹ħ
    0.10
    ÑĤÑĥÑĢ
    0.10
    ä¸įæĺİ
    0.10
     minded
    0.10
    çĻĸ
    0.10
    æªĶ
    0.10
    ories
    0.09
    cz
    0.09
    Activations Density 0.076%

    No Known Activations