© 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. 30556
    Prev
    Next
    INDEX
    Explanations

    material or content

    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
    æĭīå¼Ģ
    -0.09
    说ä¸įåĩº
    -0.09
    rams
    -0.08
    åıijå±ķä¸Ń
    -0.08
    æ²¥
    -0.08
    æ´Ĺå¹²åĩĢ
    -0.08
    onal
    -0.08
    Ñģке
    -0.08
    è´µæĹı
    -0.08
    æĹ¥æĬ¥ç¤¾
    -0.08
    POSITIVE LOGITS
    åĨħ容
    0.18
    åħ§å®¹
    0.16
     content
    0.15
     ëĤ´ìļ©
    0.14
     contenido
    0.14
    content
    0.13
    çļĦåĨħ容
    0.12
     contenu
    0.12
    éĩįè¦ģåĨħ容
    0.12
    	content
    0.11
    Activations Density 0.080%

    No Known Activations