© 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. 11944
    Prev
    Next
    INDEX
    Explanations

    tense, past, aspect

    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
    ypad
    -0.09
     pedestal
    -0.08
    innen
    -0.08
    (fl
    -0.08
    /trunk
    -0.08
    .Fl
    -0.08
    .ga
    -0.08
    ALLE
    -0.08
    WND
    -0.08
    [to
    -0.08
    POSITIVE LOGITS
     tense
    0.11
    æĢģ
    0.11
    è¯Ńæ³ķ
    0.10
    æŶæķĪ
    0.10
    è¿ĩäºĨ
    0.09
     اÙĦÙħاضÙĬ
    0.09
    åŀ©
    0.09
    Past
    0.09
    æ»ŀ
    0.09
    æĤĦæĤĦ
    0.09
    Activations Density 0.040%

    No Known Activations