© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9312
    Prev
    Next
    INDEX
    Explanations

    lift or lifted 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
    cul
    -0.12
    al
    -0.09
    æŀģåĬĽ
    -0.09
    brush
    -0.09
    pc
    -0.09
    pm
    -0.09
    ä¸ŀ
    -0.08
    jang
    -0.08
    culo
    -0.08
    ä¸ĵå¿ĥ
    -0.08
    POSITIVE LOGITS
    ä¸Ģè§Ĵ
    0.13
     lift
    0.12
    _lift
    0.12
     Lift
    0.11
     lifting
    0.11
     lifted
    0.11
    .lift
    0.10
    lift
    0.10
     khá»ıi
    0.10
    åºıå¹ķ
    0.10
    Activations Density 0.027%

    No Known Activations