© 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. 54939
    Prev
    Next
    INDEX
    Explanations

    Possessive 's after 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
    _icall
    -0.11
    -mf
    -0.10
    FRING
    -0.09
    ãĤŃãĥ³ãĤ°
    -0.09
    irts
    -0.09
    Perm
    -0.09
     Perm
    -0.09
    ÙĬÙĤ
    -0.09
    lickr
    -0.09
    /inet
    -0.09
    POSITIVE LOGITS
    \_
    0.10
    为主é¢ĺçļĦ
    0.10
    为主çļĦ
    0.10
    çļĦ人æĿ¥è¯´
    0.09
    ”çļĦ
    0.08
    -to
    0.08
    -from
    0.08
     project
    0.08
    ä¼ĹçŃ¹
    0.08
    -by
    0.08
    Activations Density 0.154%

    No Known Activations