© 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. 26999
    Prev
    Next
    INDEX
    Explanations

    and I

    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
    å¼ĤæĢ§
    -0.10
    寨
    -0.10
    çľ¼åīįçļĦ
    -0.09
    æĪIJå°±æĦŁ
    -0.09
    hoe
    -0.09
    å¤
    -0.09
    REFERENCE
    -0.09
    æ¡ĥèĬ±
    -0.08
    çĶļèĩ³æĺ¯
    -0.08
    _PLATFORM
    -0.08
    POSITIVE LOGITS
    åħ¨å¥Ĺ
    0.10
    ÑģÑĤанавлива
    0.09
    Nom
    0.08
    åĮĹæµ·
    0.08
    èī°éļ¾
    0.08
    견
    0.08
    éĶ¡
    0.08
    è§Ħéģ¿
    0.08
    çĭİ
    0.08
    Ghost
    0.08
    Activations Density 0.028%

    No Known Activations