© 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. 27781
    Prev
    Next
    INDEX
    Explanations

    advent of

    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
    ãĥĥãĥī
    -0.09
    sing
    -0.09
    oppers
    -0.09
    allet
    -0.09
    çĪ±ç¾İ
    -0.09
     занÑıÑĤ
    -0.08
    å»ĵ
    -0.08
    åľ¨åħ¨åĽ½
    -0.08
    untu
    -0.08
    NOP
    -0.08
    POSITIVE LOGITS
     bucks
    0.10
    涯
    0.09
    ues
    0.09
    让èĩªå·±
    0.09
    åĮĸ解
    0.09
    tees
    0.08
    ç»Ļèĩªå·±
    0.08
    èIJģ
    0.08
    æĪIJçĨŁ
    0.08
    对èĩªå·±çļĦ
    0.08
    Activations Density 0.002%

    No Known Activations