© 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. 10086
    Prev
    Next
    INDEX
    Explanations

    jacob and related names/relationships

    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
    fully
    -0.10
    ful
    -0.09
    roy
    -0.09
     rÃłng
    -0.09
    igi
    -0.09
    erv
    -0.09
    FUL
    -0.08
    ner
    -0.08
    imore
    -0.08
    amp
    -0.08
    POSITIVE LOGITS
    son
    0.15
    sons
    0.15
    bole
    0.13
    à¹Į
    0.12
    abad
    0.12
    rig
    0.11
    SON
    0.10
    owitz
    0.10
    ä½ıäºĨ
    0.10
    ãĤĤãģ®
    0.10
    Activations Density 0.036%

    No Known Activations