© 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. 38260
    Prev
    Next
    INDEX
    Explanations

    time of day/week

    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
    ucid
    -0.09
     LCS
    -0.08
    ecn
    -0.08
     Eck
    -0.08
    èģĶ
    -0.08
    æĦļ
    -0.08
    个ä½ĵ
    -0.08
    amina
    -0.08
    GP
    -0.08
    gp
    -0.08
    POSITIVE LOGITS
    _unpack
    0.09
    åĥµ
    0.09
    浸
    0.09
    ัà¸ĩ
    0.09
    åĸĭ
    0.09
    ses
    0.08
    èĶĵ
    0.08
    åĵij
    0.08
    å±ķæľĽ
    0.08
    èŀ«
    0.08
    Activations Density 0.025%

    No Known Activations