© 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. 35762
    Prev
    Next
    INDEX
    Explanations

    either or

    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
    yme
    -0.10
    çĶļèĩ³
    -0.10
    å¸ĥ
    -0.10
    æĺķ
    -0.09
    anchor
    -0.09
    (anchor
    -0.08
    æĹłåħ³
    -0.08
    .anchor
    -0.08
    anchors
    -0.08
    æĢĽ
    -0.08
    POSITIVE LOGITS
     equivalent
    0.12
    è¦ģä¸įçĦ¶
    0.11
     Equivalent
    0.10
    ä¸įçĦ¶
    0.10
    ä¸įä½İäºİ
    0.10
    è¶³å¤ŁçļĦ
    0.10
    èĥ½åľ¨
    0.10
    Equivalent
    0.09
    åIJ¦åĪĻ
    0.09
    缸å½ĵäºİ
    0.09
    Activations Density 0.076%

    No Known Activations