© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10505
    Prev
    Next
    INDEX
    Explanations

    technical information and concepts

    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
    æĪĸå¤ļ
    -0.11
    arez
    -0.10
    åĴĮ个人
    -0.09
    åĴĮä»ĸçļĦ
    -0.09
    åı¯åĪĨ为
    -0.09
    ä¸ĩä¸Ģ
    -0.09
    å´¦
    -0.08
    ormap
    -0.08
    @hotmail
    -0.08
    .ld
    -0.08
    POSITIVE LOGITS
     respectively
    0.15
     alike
    0.14
    éĥ½éĿŀ常
    0.12
    ãģĿãĤĮãģŀãĤĮ
    0.10
    éĥ½æĹłæ³ķ
    0.10
    éĥ½å¾Ī
    0.10
    éĥ½åºĶ该
    0.10
    以åıĬåħ¶ä»ĸ
    0.09
    respect
    0.09
     serta
    0.09
    Activations Density 1.008%

    No Known Activations