© 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. 4636
    Prev
    Next
    INDEX
    Explanations

    royal titles and associated 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
    ting
    -0.10
    ary
    -0.09
    ink
    -0.09
    á»ijng
    -0.08
     Manit
    -0.08
    è¿Ļä½į
    -0.08
    سÙĦ
    -0.08
    cludes
    -0.08
    ãģĦãģĨ
    -0.08
    æ´½
    -0.08
    POSITIVE LOGITS
    ¾
    0.11
    çĪ·
    0.11
    ically
    0.10
    éĻĽä¸ĭ
    0.10
    hood
    0.10
    auté
    0.10
    liness
    0.09
    éĤ¸
    0.09
    itus
    0.09
    iser
    0.09
    Activations Density 0.163%

    No Known Activations