© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 55933
    Prev
    Next
    INDEX
    Explanations

    anywhere else

    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
    åij½
    -0.10
    åľ¨éĩĮéĿ¢
    -0.10
    æĹĥ
    -0.09
    æĪİ
    -0.09
    æĢĢ
    -0.09
    Sou
    -0.09
    æijĨåľ¨
    -0.09
    åıijè¨Ģ人
    -0.08
    ä»İä¸Ń
    -0.08
    çĿ¿
    -0.08
    POSITIVE LOGITS
     else
    0.12
    ä»Ģä¹Īåľ°æĸ¹
    0.10
    å¹³åı°ä¸Ĭ
    0.10
    çݯå¢ĥä¸Ń
    0.09
    ecimal
    0.09
    æķ²
    0.09
    产ä¸ļéĵ¾
    0.09
    ä¸Ģç«Ļ
    0.09
    çĶŁäº§åĴĮ
    0.09
    çĶŁæ´»ä¸Ń
    0.09
    Activations Density 0.052%

    No Known Activations