© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19999
    Prev
    Next
    INDEX
    Explanations

    URL domain names

    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
    eenth
    -0.12
    ein
    -0.09
    ../
    -0.09
    grund
    -0.09
    istra
    -0.09
    eus
    -0.09
    ees
    -0.08
    posites
    -0.08
    istic
    -0.08
    posite
    -0.08
    POSITIVE LOGITS
    ëģĶ
    0.12
    人éĢī
    0.10
    esus
    0.09
    doi
    0.09
    obra
    0.09
    æ´ĹèĦ¸
    0.09
    年人
    0.09
    æĪĺçķ¥æĢ§
    0.09
    /operators
    0.09
    é³Ŀ
    0.09
    Activations Density 0.166%

    No Known Activations