© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 17563
    Prev
    Next
    INDEX
    Explanations

    fundamentals and company value

    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
    ä¸įæĪIJ
    -0.08
    æ¤į
    -0.08
    _TM
    -0.08
    æīģ
    -0.08
    梯
    -0.08
    ÑĤиÑĢов
    -0.08
    躺
    -0.08
    uard
    -0.08
     Connie
    -0.08
    æĥº
    -0.08
    POSITIVE LOGITS
    åŁºæľ¬éĿ¢
    0.16
    åīįéĢĶ
    0.11
     underlying
    0.10
     Tap
    0.10
     fundamentals
    0.10
    ä¸ļ绩
    0.10
    æĿĥéĩį
    0.10
    Tap
    0.10
    hots
    0.09
     tap
    0.09
    Activations Density 0.047%

    No Known Activations