© 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. 10481
    Prev
    Next
    INDEX
    Explanations

    with/without or no, followed by outcome

    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
    çĴ¨
    -0.10
    ä¸Ģç¯ĩæĸĩç«ł
    -0.09
    ensen
    -0.09
    端æŃ£
    -0.09
    ä¸Ģè´¯
    -0.09
    åĬ¼
    -0.09
    wm
    -0.09
    cies
    -0.08
    è¿Ļæīįæĺ¯
    -0.08
    arel
    -0.08
    POSITIVE LOGITS
    æķĪæŀľ
    0.16
    æĪIJæķĪ
    0.15
     effect
    0.13
    çļĦæķĪæŀľ
    0.11
    好å¤Ħ
    0.11
    åIJİæŀľ
    0.10
    .effect
    0.10
    å¾Ī好
    0.10
     Effect
    0.10
    Effect
    0.10
    Activations Density 0.076%

    No Known Activations