© 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. 33465
    Prev
    Next
    INDEX
    Explanations

    abbreviations and acronyms

    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
    æ¶īåıĬåĪ°
    -0.10
    æ¶īåıĬ
    -0.10
    åĮ£
    -0.09
    fest
    -0.08
    æĢİä¹Īçľĭ
    -0.08
    èĿł
    -0.08
    åijIJ
    -0.08
    ãģĿãĤĮãģ§ãĤĤ
    -0.08
    yyy
    -0.08
    è¿Ļç¯ĩ
    -0.08
    POSITIVE LOGITS
    оÑĢÑĤ
    0.10
    å¥
    0.10
    åĿĢ
    0.09
    å®Ľ
    0.09
    åīį身
    0.09
    çļĦéĴ±
    0.09
    umph
    0.09
    è¿Ĥ
    0.09
     %{
    0.09
    èĩ´åĬĽ
    0.08
    Activations Density 0.122%

    No Known Activations