© 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. 50925
    Prev
    Next
    INDEX
    Explanations

    heard from

    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
    说çļĦè¯Ŀ
    -0.09
    çľĭå¾ħ
    -0.09
    éĻħ
    -0.09
    说æĪij
    -0.09
    æ´ŀå¯Ł
    -0.08
    -con
    -0.08
    èĮµ
    -0.08
    imentos
    -0.08
    gui
    -0.07
    .spec
    -0.07
    POSITIVE LOGITS
    éĶ·
    0.10
    åı¯ä¿¡
    0.10
    管ç½ij
    0.09
    تÙĪج
    0.09
    å¾ij
    0.09
    /set
    0.09
    离
    0.09
    å±ģ
    0.09
    èħ¼
    0.09
    èİĽ
    0.09
    Activations Density 0.008%

    No Known Activations