© 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. 3161
    Prev
    Next
    INDEX
    Explanations

    riding in or on something

    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
    ensa
    -0.11
    кÑĥп
    -0.10
    IMP
    -0.09
    ä¹į
    -0.09
    èµŀ
    -0.09
    abies
    -0.09
    abor
    -0.09
    ãĥ¡ãĥ³ãĥĪ
    -0.08
    æĭĶ
    -0.08
    SID
    -0.08
    POSITIVE LOGITS
    лов
    0.09
    æĤł
    0.08
    å·¡è§Ĩ
    0.08
    æĴµ
    0.08
    å·¡åĽŀ
    0.08
    åľ¨å¹¿å·ŀ
    0.08
     Throne
    0.08
    íĥľ
    0.07
    oha
    0.07
     serializers
    0.07
    Activations Density 0.027%

    No Known Activations