© 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. 37325
    Prev
    Next
    INDEX
    Explanations

    musings

    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
    ish
    -0.09
    outs
    -0.09
    most
    -0.09
    ร
    -0.09
    rew
    -0.09
    ÑĪе
    -0.09
    èĬ±å¼Ģ
    -0.08
    åıĭåĸĦ
    -0.08
    share
    -0.08
    ity
    -0.08
    POSITIVE LOGITS
    窿
    0.13
    htar
    0.11
    fully
    0.10
    forge
    0.10
    afa
    0.10
    acles
    0.10
    ãĥ¬ãĥ¼ãĤ·ãĥ§ãĥ³
    0.10
    etically
    0.09
    esz
    0.09
    橱
    0.09
    Activations Density 0.005%

    No Known Activations