© 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. 21769
    Prev
    Next
    INDEX
    Explanations

    such a

    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
    æĴŀ
    -0.08
    å®ŀè´¨
    -0.08
     >>
    -0.07
    ми
    -0.07
    ãĥ¡ãĥ³ãĥĪ
    -0.07
     correct
    -0.07
    漫
    -0.07
     ex
    -0.07
    è¾¾
    -0.07
    gm
    -0.07
    POSITIVE LOGITS
    éĩįè¦ģçļĦ
    0.11
    èį¼
    0.10
    è¿ĻèĪ¬
    0.10
    è¨ĢãĤıãĤĮ
    0.10
    å¦ĤæѤ
    0.10
    ç¦ıå¾·
    0.10
    ç¾İ好çļĦ
    0.10
    erule
    0.10
    lingen
    0.09
    еÑĢж
    0.09
    Activations Density 0.042%

    No Known Activations