© 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. 29940
    Prev
    Next
    INDEX
    Explanations

    frankly speaking

    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
    -0.09
    æ¸Ń
    -0.08
    æī«ä¸Ģæī«
    -0.08
    轨
    -0.08
    èĢ¿
    -0.08
     proverb
    -0.08
    ç¿»
    -0.08
     Bailey
    -0.08
    两边
    -0.08
     dl
    -0.08
    POSITIVE LOGITS
     ÐĶмиÑĤÑĢ
    0.10
    æįŁå®³
    0.09
    umat
    0.09
    LER
    0.09
    uell
    0.08
    $tpl
    0.08
    áf
    0.08
    ils
    0.08
    oub
    0.08
    æĸĩæĺĮ
    0.08
    Activations Density 0.052%

    No Known Activations