© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 972
    Prev
    Next
    INDEX
    Explanations

    biological

    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
    ature
    -0.10
    å·©
    -0.10
    ifiable
    -0.09
    妫
    -0.09
    icular
    -0.09
    åŃIJéĩĮ
    -0.09
    erah
    -0.08
    busters
    -0.08
    osa
    -0.08
    rott
    -0.08
    POSITIVE LOGITS
    ALLY
    0.11
    èŁ¹
    0.10
    anded
    0.10
    /math
    0.09
    ically
    0.09
    endas
    0.09
    åŃ¦å®¶
    0.09
    ìłģìľ¼ë¡ľ
    0.09
    åĭĥåĭĥ
    0.09
    ema
    0.09
    Activations Density 0.046%

    No Known Activations