© 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. 21414
    Prev
    Next
    INDEX
    Explanations

    both ... of/are

    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
    ously
    -0.10
    orbit
    -0.10
     ÙĪاØŃدة
    -0.09
    both
    -0.09
    ç§įç§į
    -0.09
    rab
    -0.08
     Filip
    -0.08
    -minded
    -0.08
    ä¸Ģ座
    -0.08
    les
    -0.08
    POSITIVE LOGITS
     sides
    0.13
     sexes
    0.13
    /all
    0.13
     kinds
    0.11
    หมà¸Ķ
    0.11
    Ñĩив
    0.10
     Seiten
    0.10
     genders
    0.10
    -sex
    0.10
    iance
    0.09
    Activations Density 0.071%

    No Known Activations