© 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. 58194
    Prev
    Next
    INDEX
    Explanations

    ski and related activities

    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
    hips
    -0.10
    ives
    -0.10
    rics
    -0.09
     Ende
    -0.09
    hift
    -0.09
    .IT
    -0.09
    å°¼æĸ¯
    -0.09
    躯
    -0.09
    adiator
    -0.09
    åĪĽä¸ļèĢħ
    -0.09
    POSITIVE LOGITS
    aru
    0.10
    verted
    0.10
    çĻ½é©¬
    0.09
    椤
    0.09
    -shadow
    0.09
    çĶ¨åĵģ
    0.09
    ernet
    0.09
    ying
    0.09
    ern
    0.09
    олÑĮз
    0.09
    Activations Density 0.007%

    No Known Activations