© 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. 21689
    Prev
    Next
    INDEX
    Explanations

    for [noun]

    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
    .other
    -0.10
     airst
    -0.09
    åİ
    -0.09
    æĮģãģ¡
    -0.09
    uters
    -0.09
    为主
    -0.09
    ä¸ķ
    -0.08
    éĻ¢éķ¿
    -0.08
    æī¬
    -0.08
    éĩijéĻµ
    -0.08
    POSITIVE LOGITS
    sdk
    0.10
     Pens
    0.09
    èĦļ
    0.09
    足
    0.09
    vu
    0.08
    æŀ¢
    0.08
    éĿ¢å®¹
    0.08
    ä¸Ģéĺµ
    0.08
    è¿Ļä¸Ģå¹´
    0.08
     whom
    0.08
    Activations Density 0.040%

    No Known Activations