© 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. 51768
    Prev
    Next
    INDEX
    Explanations

    trading, bull, trader, money

    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
    æį¢
    -0.09
    æıĽ
    -0.09
    ä¹ĺ
    -0.08
    ä¸Ģçķª
    -0.08
    æĻļæľŁ
    -0.08
     Weeks
    -0.08
    åħĭèݱ
    -0.08
    æĽ¿
    -0.08
    è´¥
    -0.08
    æĽ²
    -0.08
    POSITIVE LOGITS
    æ¸ħç®Ĺ
    0.11
    å½Ń
    0.11
    交æĺĵ
    0.10
    åįģåĪĨéĴŁ
    0.10
    bull
    0.09
     Ninja
    0.09
     blot
    0.09
    æĢµ
    0.09
    交æĺĵå¹³åı°
    0.09
     trader
    0.09
    Activations Density 0.115%

    No Known Activations