© 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. 58918
    Prev
    Next
    INDEX
    Explanations

    Laguna, Lagos, Bermuda, ago

    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
    loom
    -0.10
    lessness
    -0.09
    presso
    -0.09
    mate
    -0.09
    most
    -0.09
    讵
    -0.08
    稿
    -0.08
     пиÑĤаниÑı
    -0.08
    rollo
    -0.08
    uto
    -0.08
    POSITIVE LOGITS
    ç¾¤å²Ľ
    0.11
    ода
    0.10
    çķĶ
    0.10
    èĻij
    0.10
    æ»ĵ
    0.09
    æ±ķ
    0.09
    篦
    0.09
    ãģ¾ãģ¾
    0.09
    æ±ł
    0.09
    é£İæĥħ
    0.09
    Activations Density 0.011%

    No Known Activations