© 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. 7273
    Prev
    Next
    INDEX
    Explanations

    knot or tie

    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
    éĵ¡
    -0.12
    ä¹ĭ人
    -0.11
    躺çĿĢ
    -0.11
    海岸
    -0.10
    éķ¬
    -0.10
    岸
    -0.10
    èĪį
    -0.10
    éĿ¢å®¹
    -0.10
    海滨
    -0.09
    çŁį
    -0.09
    POSITIVE LOGITS
    ç»ĵ
    0.11
     knot
    0.10
     knots
    0.10
     Knot
    0.10
    çµIJ
    0.10
    æīĵ好
    0.09
    æĭ³å¤´
    0.08
    attended
    0.08
    nore
    0.08
    èķĻ
    0.08
    Activations Density 0.022%

    No Known Activations