© 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. 61247
    Prev
    Next
    INDEX
    Explanations

    quantum information and measurement

    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
     min
    -0.10
    .getInteger
    -0.09
    auer
    -0.09
    æĬł
    -0.09
    åįĩ
    -0.09
    åįĩéĻį
    -0.09
    æ³ķå¾ĭ顾éĹ®
    -0.08
    以为
    -0.08
    å¡ŀ
    -0.08
    èĮķ
    -0.08
    POSITIVE LOGITS
    è§Ĥ
    0.11
    è§Ĥæµĭ
    0.10
     reels
    0.09
    è·Łè¸ª
    0.09
    æľ¬äºº
    0.09
    éĶŁ
    0.09
    jad
    0.08
    ÙĪات
    0.08
    Tracking
    0.08
    è§Ģ
    0.08
    Activations Density 0.085%

    No Known Activations