© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37068
    Prev
    Next
    INDEX
    Explanations

    look at / for / around / forward / out

    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
    ÑĢод
    -0.10
    MENT
    -0.10
    çľĭä¼¼
    -0.10
    ä½łçľĭ
    -0.09
    forth
    -0.09
    çľĭä¸Ĭåİ»
    -0.09
    ilt
    -0.09
    hog
    -0.09
    æĪijåİ»
    -0.09
    -looking
    -0.09
    POSITIVE LOGITS
    AndFeel
    0.14
    AndServe
    0.13
    å²±
    0.11
    еÑĤÑĮ
    0.11
    ings
    0.11
    iness
    0.11
    OrCreate
    0.10
    ä¸Ģçľ¼
    0.10
    ahead
    0.10
    ä¸įåĩºæĿ¥
    0.09
    Activations Density 0.061%

    No Known Activations