© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38467
    Prev
    Next
    INDEX
    Explanations

    move forward or away

    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
    /on
    -0.10
    èł¹
    -0.09
    ãĤ¦ãĤ©
    -0.09
    /from
    -0.09
    gh
    -0.09
    sports
    -0.09
    夯
    -0.09
    æ¦Ľ
    -0.09
    ÑĪив
    -0.09
    ries
    -0.09
    POSITIVE LOGITS
    åľ°å¸¦
    0.10
     consect
    0.09
    æ¸Ń
    0.08
    éŀĺ
    0.08
    å¥
    0.08
    GC
    0.08
     esl
    0.08
    æĤ²åĵĢ
    0.08
    carry
    0.08
    led
    0.08
    Activations Density 0.027%

    No Known Activations