© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10094
    Prev
    Next
    INDEX
    Explanations

    ez ending

    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
    istic
    -0.10
    ily
    -0.10
    çĮ¢
    -0.09
    äºĨ大éĩıçļĦ
    -0.09
    ish
    -0.09
    t
    -0.09
    ingly
    -0.08
    acz
    -0.08
    ê¹IJ
    -0.08
    awan
    -0.08
    POSITIVE LOGITS
    ÑģÑı
    0.10
    åĦ¿å¥³
    0.10
    -vous
    0.09
     Mund
    0.09
     позв
    0.09
    íĴĪ
    0.09
    èĤ©
    0.09
    ëģĶ
    0.09
    cona
    0.09
    æºIJ头
    0.08
    Activations Density 0.007%

    No Known Activations