© 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. 56334
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by opinions or attributes

    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
    orra
    -0.10
    aken
    -0.09
    Dean
    -0.09
    éĹ¾
    -0.09
     khuôn
    -0.09
    身边çļĦ
    -0.08
    身å¿ĥåģ¥åº·
    -0.08
    æ°Ľ
    -0.08
    å±ĢåĬ¿
    -0.08
    åįł
    -0.08
    POSITIVE LOGITS
     Palin
    0.09
    çļĦåŃ©åŃIJ
    0.08
    ç¹ģ
    0.08
    æ¶īåıĬåĪ°
    0.08
     Heard
    0.08
    ichtig
    0.07
    åĹŁ
    0.07
    изаÑĨии
    0.07
     schl
    0.07
    ensed
    0.07
    Activations Density 0.027%

    No Known Activations