© 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. 34153
    Prev
    Next
    INDEX
    Explanations

    album titles and names

    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
    对åħ¶
    -0.09
    姿
    -0.08
    姿åĬ¿
    -0.08
    æĪĸå°Ĩ
    -0.08
    é²ł
    -0.08
     Thunder
    -0.08
    é»ĺ
    -0.08
    è¦ģä¹Ī
    -0.08
    Digest
    -0.08
    对该
    -0.08
    POSITIVE LOGITS
    æ¹Ľ
    0.10
    ÑĩÑĥ
    0.09
    cams
    0.09
    æľ¬äºº
    0.09
    ä¸Ģç¯ĩ
    0.09
    ucene
    0.08
    rails
    0.08
    .appspot
    0.08
    èĪŀ
    0.08
    äl
    0.08
    Activations Density 0.056%

    No Known Activations