© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2130
    Prev
    Next
    INDEX
    Explanations

    possessive pronoun for female

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    éħįåIJĪ
    -0.28
    mate
    -0.23
    udd
    -0.23
    care
    -0.23
     focus
    -0.23
    Focus
    -0.22
    ception
    -0.22
     coc
    -0.22
    æ°ijåĽ½
    -0.22
    å¤ļ个
    -0.22
    POSITIVE LOGITS
    wick
    0.24
    opies
    0.23
    :pk
    0.23
    éħ£
    0.22
    ä¿©
    0.21
    è¶ħé¢Ŀ
    0.21
    ä¸Ĭåı¸
    0.21
    ihad
    0.21
    nation
    0.21
    archy
    0.21
    Activations Density 0.142%

    No Known Activations