© 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. 50283
    Prev
    Next
    INDEX
    Explanations

    Newtown and Newton places/people

    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
    onaut
    -0.10
    ophile
    -0.09
    ono
    -0.09
    ãĥĬãĥ«
    -0.09
    ëĦIJ
    -0.08
    anst
    -0.08
    Ľ
    -0.08
    ibal
    -0.08
    ouble
    -0.08
    æī¬å·ŀ
    -0.08
    POSITIVE LOGITS
    çĪµå£«
    0.11
    .Unity
    0.10
    æ¯ĶåĪĨ
    0.09
    é©Ń
    0.09
    OLVE
    0.09
    coma
    0.09
    ä½ľåĿĬ
    0.08
    اع
    0.08
    侯
    0.08
    IZER
    0.08
    Activations Density 0.003%

    No Known Activations