© 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. 35677
    Prev
    Next
    INDEX
    Explanations

    pretty sure/much/new

    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
    sWith
    -0.11
    éĩįéĩį
    -0.09
    éķŃ
    -0.09
    çľ¼çķĮ
    -0.08
    TintColor
    -0.08
    æŀģåħ¶
    -0.08
    ä¸Ģ次
    -0.08
    èĴ¯
    -0.08
    idable
    -0.08
    иÑĩеÑģкÑĥÑİ
    -0.08
    POSITIVE LOGITS
    说æĺ¯
    0.13
    说æĪij
    0.12
    fall
    0.12
     обеÑģп
    0.11
    ä¹ħäºĨ
    0.10
    comings
    0.10
    ening
    0.10
    éħ£
    0.10
    à¹Ĩ
    0.09
    udy
    0.09
    Activations Density 0.013%

    No Known Activations