© 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. 21520
    Prev
    Next
    INDEX
    Explanations

    Alliance for

    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
    ly
    -0.12
    åĦ¿
    -0.11
    ially
    -0.11
    illion
    -0.11
    ture
    -0.10
    linger
    -0.10
    lings
    -0.10
    illac
    -0.09
    ities
    -0.09
     chuyá»ĩn
    -0.09
    POSITIVE LOGITS
    igator
    0.11
    arity
    0.11
     Franç
    0.10
    chaft
    0.10
    andro
    0.09
    aire
    0.09
    andy
    0.09
    -building
    0.08
    unny
    0.08
    ignment
    0.08
    Activations Density 0.014%

    No Known Activations