© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 50780
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥŁãĥ³ãĤ°
    -0.08
    °
    -0.08
    zilla
    -0.08
    è¦ģä¹Ī
    -0.08
     bowiem
    -0.07
    æ²½
    -0.07
     entweder
    -0.07
    IFI
    -0.07
    sess
    -0.07
    acr
    -0.07
    POSITIVE LOGITS
     its
    0.11
    缸åºĶçļĦ
    0.10
     Its
    0.10
    Its
    0.09
    缸åºĶ
    0.09
     corresponding
    0.09
    缸æĩī
    0.08
    äºĨåħ¶
    0.08
    åħ¶ä¸İ
    0.08
    æľīåħ¶
    0.08
    Activations Density 0.395%

    No Known Activations