© 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. 22710
    Prev
    Next
    INDEX
    Explanations

    will have/be

    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
    æĭİ
    -0.11
    ä»Ģä¹ĪåİŁåĽł
    -0.10
    æĥ³åĬŀæ³ķ
    -0.10
    åįģ足
    -0.09
    åĮħ裹
    -0.09
    èĩªæķij
    -0.09
    à¸Ĭะ
    -0.09
    åijĬè¯īæĪij们
    -0.09
    çĪ¨
    -0.08
    ç®IJ
    -0.08
    POSITIVE LOGITS
    åľ¨æľªæĿ¥
    0.10
    å±ĬæŶ
    0.10
    é¢Ħè§ģ
    0.10
    ä»ĬåIJİ
    0.09
     future
    0.09
    æݥ触åĪ°
    0.08
    å°ĨæĿ¥
    0.08
    佬
    0.08
    é¢ĦæĸĻ
    0.08
     Likely
    0.08
    Activations Density 0.105%

    No Known Activations