© 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. 2539
    Prev
    Next
    INDEX
    Explanations

    philosophy and related thoughts

    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
    笼
    -0.09
    ä»Ģä¹ĪæŶåĢĻ
    -0.09
    æİł
    -0.09
    mage
    -0.09
    estic
    -0.09
    ä¸ĭåİ»
    -0.08
    ä¸ĭ车
    -0.08
    æ·±å±Ĥ次
    -0.08
    alive
    -0.08
    åħħæ²Ľ
    -0.08
    POSITIVE LOGITS
    æ³ķåĪ¶
    0.09
    对ç«ĭ
    0.09
    æĺī
    0.08
    uria
    0.08
    ippers
    0.08
     nip
    0.08
    æµ·ä¸Ĭ
    0.08
    çħ¨
    0.08
     assignable
    0.08
     Atkins
    0.08
    Activations Density 0.018%

    No Known Activations