© 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. 27863
    Prev
    Next
    INDEX
    Explanations

    elle ending in e

    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
    æľįå½¹
    -0.10
    .tie
    -0.10
    çĸ¯çĭĤ
    -0.10
    éĹªçĶµ
    -0.10
    å¼¹
    -0.09
    ileged
    -0.09
    à¸Ĺรà¸ĩ
    -0.09
    éļľç¢į
    -0.09
    _ASM
    -0.09
    çĶ¨åľ°
    -0.09
    POSITIVE LOGITS
     вÑģÑĤÑĢ
    0.09
    referrer
    0.09
    uces
    0.08
    åĴ§
    0.08
     wishes
    0.08
    رÙĬد
    0.08
    çģĮ
    0.08
    ç½®
    0.08
     extra
    0.08
    extra
    0.08
    Activations Density 0.132%

    No Known Activations