© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8963
    Prev
    Next
    INDEX
    Explanations

    culminating in, climaxes in

    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
    çķĮçļĦ
    -0.09
    akes
    -0.09
    liness
    -0.09
    é¾Ī
    -0.09
    ÑģÑĤÑĮ
    -0.08
    éŃĤ
    -0.08
    èĬĬ
    -0.08
    èľļ
    -0.08
    积æŀģæĢ§
    -0.08
    -UA
    -0.08
    POSITIVE LOGITS
    cul
    0.11
     cul
    0.10
    æľīä¸Ģ天
    0.09
    глав
    0.09
    =end
    0.09
    astr
    0.09
    è¿ĻçĤ¹
    0.08
     efforts
    0.08
    ãĤĴè¿İ
    0.08
    çĺģ
    0.08
    Activations Density 0.018%

    No Known Activations