© 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. 48459
    Prev
    Next
    INDEX
    Explanations

    past tense and present participles

    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
    rema
    -0.09
    Catch
    -0.09
    åĮĹ京æŶéĹ´
    -0.09
    ainment
    -0.09
    affle
    -0.09
    PropertyParams
    -0.09
     ÅĽw
    -0.09
    ãŁ
    -0.09
    _THREADS
    -0.09
    oola
    -0.08
    POSITIVE LOGITS
    edia
    0.09
    为代表
    0.09
    cord
    0.09
    éĤ£æ¬¡
    0.09
    äºĨå¤ļå°ij
    0.09
    ä½ı
    0.08
    æĭ³
    0.08
    bsp
    0.08
    æIJ¬åĪ°
    0.08
    éĹŃ
    0.08
    Activations Density 0.029%

    No Known Activations