© 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. 52859
    Prev
    Next
    INDEX
    Explanations

    financial services and markets

    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
    ÅĤow
    -0.09
    _FS
    -0.09
    åĴĮå®ĮåĸĦ
    -0.09
    éĩįä¸Ń
    -0.09
    åĥµ
    -0.09
    æĭĤ
    -0.09
    åŁºéĩij管çIJĨ
    -0.09
    çĹķ迹
    -0.08
    aben
    -0.08
    åı«å£°
    -0.08
    POSITIVE LOGITS
    -grade
    0.10
    ë§Ŀ
    0.09
    atter
    0.09
    大家åĪĨ享
    0.09
    涴
    0.08
    çķ´
    0.08
    çķĮ
    0.08
    è°ĭ
    0.08
    åĬŁå¾·
    0.08
    å¼ºåĽ½
    0.08
    Activations Density 0.016%

    No Known Activations