© 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. 39078
    Prev
    Next
    INDEX
    Explanations

    reflexive pronouns

    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
    èĩªå·±çļĦ
    -0.12
    itional
    -0.09
     scl
    -0.09
    æ»ĵ
    -0.09
    她çļĦ
    -0.09
    éĶĻ
    -0.09
    heads
    -0.08
    çĥĪ
    -0.08
    ery
    -0.08
    ching
    -0.08
    POSITIVE LOGITS
    verständlich
    0.17
     Tanner
    0.10
    岿
    0.10
    nya
    0.10
    åĪİ
    0.10
    воÑĢ
    0.10
    riad
    0.10
    åĿļæĮģä¸įæĩĪ
    0.09
    è£Ĩ
    0.09
    aint
    0.09
    Activations Density 0.044%

    No Known Activations