© 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. 57869
    Prev
    Next
    INDEX
    Explanations

    locations or times

    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
    abal
    -0.09
    ounce
    -0.08
    绿èī²
    -0.08
    å¤Ł
    -0.08
    æľ¬åľºæ¯ĶèµĽ
    -0.08
     prof
    -0.08
    åľ¨è¿Ļ
    -0.08
    åī¯éĻ¢éķ¿
    -0.08
    æģ³
    -0.07
     cent
    -0.07
    POSITIVE LOGITS
    éļıæŶéļıåľ°
    0.10
    éľĨ
    0.10
    æĻ¨
    0.10
    åĽŀéģ¿
    0.10
    åĿIJåľ¨
    0.10
    è¾¹
    0.09
    æŀķ
    0.09
    æ´Ĺæīĭ
    0.09
    çĿ¡åīį
    0.09
     spare
    0.09
    Activations Density 0.077%

    No Known Activations