© 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. 5522
    Prev
    Next
    INDEX
    Explanations

    detection and calculation verbs

    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
    æĢİä¹ĪåĬŀ
    -0.10
    esa
    -0.10
    天æĸĩ
    -0.09
     ÑĢож
    -0.09
    à¹ģห
    -0.09
    تÙĩا
    -0.09
    год
    -0.09
    ä¹ĭåľ°
    -0.09
    otts
    -0.09
    زار
    -0.08
    POSITIVE LOGITS
    äºĨä¸Ģæī¹
    0.09
    à¦ĸ
    0.09
    LEC
    0.09
    御
    0.08
    untime
    0.08
    äºĨä¸Ģç³»åĪĹ
    0.08
    åĺ¹
    0.08
    è¾ĸåĮºåĨħ
    0.08
     advent
    0.08
    ä¸Ģæī¹
    0.08
    Activations Density 0.700%

    No Known Activations