© 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. 36864
    Prev
    Next
    INDEX
    Explanations

    attorney and legal proceedings

    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
    ëģĶ
    -0.15
    -0.11
    常å§Ķä¼ļ
    -0.10
    tures
    -0.10
    ½
    -0.09
    lings
    -0.09
    imum
    -0.08
    æĮģãģ¡
    -0.08
    otta
    -0.08
    .Toolkit
    -0.08
    POSITIVE LOGITS
    ties
    0.12
    istic
    0.11
    ships
    0.10
    ship
    0.10
    chants
    0.10
    ศาส
    0.09
    说æĺ¯
    0.09
    AGE
    0.09
    oblin
    0.09
    resses
    0.09
    Activations Density 0.026%

    No Known Activations