© 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. 7848
    Prev
    Next
    INDEX
    Explanations

    compile error

    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
    ened
    -0.13
    lessly
    -0.11
    OfFile
    -0.10
    inally
    -0.10
    est
    -0.09
    esting
    -0.09
    ening
    -0.09
    unci
    -0.09
    -than
    -0.09
    尾巴
    -0.09
    POSITIVE LOGITS
    ares
    0.13
    aries
    0.11
    forme
    0.10
    tron
    0.10
    arf
    0.10
    cran
    0.09
    azon
    0.09
     iT
    0.09
    ä½ĵåĨħ
    0.09
    tures
    0.09
    Activations Density 0.047%

    No Known Activations