© 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. 56293
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by devices/programs

    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
    è¡¿
    -0.10
    æĭ£
    -0.10
     ÄijÄĥng
    -0.09
     ÑĤебе
    -0.09
    ä¹¾åĿ¤
    -0.09
     lẽ
    -0.09
    .INVALID
    -0.08
    ç©´
    -0.08
    è¿Ļ件
    -0.08
    è··
    -0.08
    POSITIVE LOGITS
    çİ°æľīçļĦ
    0.10
    社ä¼ļç»Ħç»ĩ
    0.09
    ä¼ģä¸ļçļĦ
    0.09
    æ·Ģ
    0.09
    caler
    0.08
    åķĨä¸ļéĵ¶è¡Į
    0.08
    åıijéħµ
    0.08
    æijĦ
    0.08
    çݯå¢ĥä¸Ń
    0.08
    ä¼ģä¸ļæıIJä¾Ľ
    0.08
    Activations Density 0.123%

    No Known Activations