© 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. 48381
    Prev
    Next
    INDEX
    Explanations

    retain or keep

    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
    emma
    -0.09
    å±ħ室
    -0.09
    å¿ĥçģµ
    -0.09
    ç°
    -0.09
    ittest
    -0.09
    ç¼Į
    -0.09
    AndWait
    -0.09
    åŃĽ
    -0.09
    äºĴ
    -0.09
    ä¸Ģ代
    -0.09
    POSITIVE LOGITS
    ä½ıäºĨ
    0.13
    çķĻä½ı
    0.11
    ä½ı
    0.10
     retaining
    0.09
    çķª
    0.09
     Competitive
    0.08
    åĴĮåıijå±ķ
    0.08
    iki
    0.08
    èĢķ
    0.08
    ä¿ĿçķĻ
    0.08
    Activations Density 0.059%

    No Known Activations