© 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. 6829
    Prev
    Next
    INDEX
    Explanations

    O' followed by different names

    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
    nya
    -0.11
    Åij
    -0.09
    благо
    -0.08
    ä¸įä¸ĭ
    -0.08
    abouts
    -0.08
    èĪ£
    -0.08
    индив
    -0.08
    nu
    -0.08
    å°ı康
    -0.08
    ObjectType
    -0.08
    POSITIVE LOGITS
    vertime
    0.15
    ngoing
    0.12
    xford
    0.12
    xygen
    0.11
    thalm
    0.11
    ceans
    0.11
    verture
    0.11
    erland
    0.11
    lymp
    0.11
    ehler
    0.10
    Activations Density 0.074%

    No Known Activations