© 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. 56458
    Prev
    Next
    INDEX
    Explanations

    parallel bus interfaces

    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
    ifest
    -0.10
    ä¸įçĶ±
    -0.10
    ä¸įä½ı
    -0.09
    æŀĦçŃij
    -0.09
    迤
    -0.09
    hone
    -0.09
    ä»
    -0.09
    å¢ĥ
    -0.09
    æĿ¥çĶµ
    -0.09
    èĥ´
    -0.08
    POSITIVE LOGITS
    å¿Ļ
    0.10
    ì¢ħ
    0.09
    宽æĿ¾
    0.09
    mort
    0.09
    Ñģол
    0.09
    ÑĢог
    0.09
    =https
    0.08
    å·¾
    0.08
     Bulk
    0.08
     vict
    0.08
    Activations Density 0.161%

    No Known Activations