© 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. 38397
    Prev
    Next
    INDEX
    Explanations

    magnetic associated phrases

    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
    otch
    -0.10
    erah
    -0.09
    alking
    -0.09
    ocols
    -0.09
    ðŁı»
    -0.08
    媳
    -0.08
    .microsoft
    -0.08
    hof
    -0.08
     оÑĤмеÑĤ
    -0.08
    à¸ĵ
    -0.08
    POSITIVE LOGITS
    åķ¸
    0.09
    鼩
    0.09
    alore
    0.09
    åĢĴåľ¨åľ°
    0.09
    éıĬ
    0.09
     mẽ
    0.09
    gable
    0.09
    ity
    0.09
    æŁ¥çľĭåħ¨æĸĩ
    0.08
    ä½ıäºĨ
    0.08
    Activations Density 0.053%

    No Known Activations