© 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. 48458
    Prev
    Next
    INDEX
    Explanations

    financial assistance, investment, borrowers

    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
    çĻ¾èĬ±
    -0.09
    è¹Ļ
    -0.09
    æĥĭ
    -0.09
    éĨª
    -0.09
    ä½
    -0.08
    交æİ¥
    -0.08
    æĦŁ
    -0.08
    lane
    -0.08
    åĩĢ
    -0.08
    orage
    -0.08
    POSITIVE LOGITS
    æĭĸ
    0.10
    游客
    0.10
    ä¸Ģç¬Ķ
    0.10
    罪
    0.09
    两级
    0.09
    _impl
    0.08
    æķijæı´
    0.08
    æ³ī
    0.08
     tourists
    0.08
     hes
    0.08
    Activations Density 0.023%

    No Known Activations