© 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. 61004
    Prev
    Next
    INDEX
    Explanations

    endless opportunities, list, stream, ocean

    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
    ä¸įä¸ĭ
    -0.09
    izations
    -0.09
    éĻ©
    -0.08
    оÑĢÑĤ
    -0.08
    apos
    -0.08
    axes
    -0.08
    ,,,,,,,,
    -0.08
    ifer
    -0.08
     omnip
    -0.08
    å¤ļéĩį
    -0.08
    POSITIVE LOGITS
     incarn
    0.09
     sclerosis
    0.09
    è¿Ļæł·çļĦè¯Ŀ
    0.09
     Frontier
    0.09
    _except
    0.09
     ÑħоÑĩ
    0.09
    менно
    0.09
    ç¦ıçĶ°
    0.09
    0.09
    NESS
    0.08
    Activations Density 0.010%

    No Known Activations