© 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. 22611
    Prev
    Next
    INDEX
    Explanations

    derived from

    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
    为åĩĨ
    -0.09
     acquaint
    -0.09
    èĮľ
    -0.09
    å°ıåŃIJ
    -0.09
    祺
    -0.08
    çĶŁäº§åĬĽ
    -0.08
    .TXT
    -0.08
    åĪļ好
    -0.08
    åħ¸åŀĭ
    -0.08
    ere
    -0.08
    POSITIVE LOGITS
    è¡į
    0.10
    èĦ±
    0.10
    derived
    0.09
    åĮį
    0.09
    æ¯į
    0.09
    æĪĸèĢħ说
    0.09
    åİŁåħĪ
    0.09
    å©¢
    0.09
    ä¹Ļçĥ¯
    0.08
     derived
    0.08
    Activations Density 0.170%

    No Known Activations