© 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. 55645
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and 's

    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
    çIJĨæĥ³
    -0.10
    羣çIJĨ
    -0.09
    çIJĨæĥ³çļĦ
    -0.08
    çģµéŃĤ
    -0.08
    ç®Ģ
    -0.08
    æĥħå¢ĥ
    -0.08
     Axel
    -0.08
    oul
    -0.08
    æ¦Ĥ念
    -0.08
    ping
    -0.08
    POSITIVE LOGITS
    为主çļĦ
    0.10
    ä½ı
    0.10
    çĶŁäº§çĶŁæ´»
    0.09
    æĮ¡ä½ı
    0.09
    æ·ij
    0.09
    æĪij们就
    0.09
    æ¶Ķ
    0.08
    èĩªå¦Ĥ
    0.08
    æĬķåħ¥åĪ°
    0.08
     hal
    0.08
    Activations Density 0.114%

    No Known Activations