© 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. 35498
    Prev
    Next
    INDEX
    Explanations

    things followed by specifiers

    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
    éĤ£åĦ¿
    -0.10
    §
    -0.09
    اÙĨÙĬØ©
    -0.09
    åİŁåĽłä¹ĭä¸Ģ
    -0.09
    çķ´
    -0.09
    ä¸Ģ个éĹ®é¢ĺ
    -0.09
    çģ¶
    -0.09
    yal
    -0.09
    æ¶īåıĬ
    -0.09
    åĵªä¸Ģ个
    -0.08
    POSITIVE LOGITS
     ÑĢа
    0.09
    æħ
    0.09
    _DER
    0.09
     Pearce
    0.08
    åĿı
    0.08
     Things
    0.08
     things
    0.08
    诸å¦Ĥ
    0.08
    phrase
    0.08
    çļĦå°ı
    0.08
    Activations Density 0.040%

    No Known Activations