© 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. 26827
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by loss

    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
    æľīæĿ¡ä»¶çļĦ
    -0.09
    æľīæĿ¡ä»¶
    -0.09
    æIJģ
    -0.08
    =length
    -0.08
    rics
    -0.08
    æĬ½
    -0.08
    .attributes
    -0.08
    stry
    -0.08
    resse
    -0.08
    ä½
    -0.07
    POSITIVE LOGITS
    unner
    0.09
    tings
    0.09
    æ¿Ģæĥħ
    0.09
     иÑģÑĤоÑĩ
    0.09
    holm
    0.09
    çĽijçĿ£
    0.09
    è³´
    0.08
    åİŁæľīçļĦ
    0.08
    å¾Ĺå¾Ī好
    0.08
    åĬ©åĬĽ
    0.08
    Activations Density 0.032%

    No Known Activations