© 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. 57872
    Prev
    Next
    INDEX
    Explanations

    to + verb

    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
    æIJ
    -0.10
    渺
    -0.10
    墨
    -0.10
    ä¸į认è¯Ĩ
    -0.09
    tring
    -0.09
    indr
    -0.09
    磼
    -0.09
    azar
    -0.09
    ä¸įéĶĻçļĦ
    -0.08
    å½±
    -0.08
    POSITIVE LOGITS
    åĭ¿
    0.10
    ä¸įè¦ģ
    0.08
    -CS
    0.08
    æ¯ĭ
    0.08
    踹
    0.08
    enames
    0.08
    .Container
    0.08
    éħ°
    0.08
    ç§ĭ
    0.08
    arak
    0.08
    Activations Density 0.109%

    No Known Activations