© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 11461
    Prev
    Next
    INDEX
    Explanations

    names of people

    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
    çĻ«
    -0.10
    佬
    -0.10
    alus
    -0.09
    miner
    -0.09
    riet
    -0.09
    æķĪ
    -0.09
    éķĹ
    -0.09
    belt
    -0.09
    éĿ¢åŃĶ
    -0.09
    åħ¥åĽŃ
    -0.09
    POSITIVE LOGITS
    鼷æĸ¯
    0.09
    Rick
    0.09
    íĸī
    0.08
    åŃľ
    0.08
    zig
    0.08
    .cms
    0.08
    عط
    0.08
    åįģåħ«
    0.08
    çIJĨç§ij
    0.08
    py
    0.08
    Activations Density 0.009%

    No Known Activations