© 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. 9691
    Prev
    Next
    INDEX
    Explanations

    the followed by specific capitalized words

    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
    1
    -0.09
    favor
    -0.08
    票
    -0.08
    åį°è±¡
    -0.08
    Realm
    -0.08
    5
    -0.08
    温馨
    -0.08
    称åij¼
    -0.08
    vert
    -0.07
    9
    -0.07
    POSITIVE LOGITS
    è®®äºĭ
    0.10
    建çŃijä¸ļ
    0.10
    çĿ£
    0.10
     ÑĪколÑĮ
    0.09
    人çļĦ
    0.09
    æ¶Į
    0.09
    æī¹
    0.09
    aries
    0.09
    èµı
    0.09
    umm
    0.09
    Activations Density 0.046%

    No Known Activations