© 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. 19410
    Prev
    Next
    INDEX
    Explanations

    own / selves

    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
    åħ¶è¡Į为
    -0.08
    åħ¶èĩªçĦ¶
    -0.08
     our
    -0.08
    å®ŀç¼´èµĦæľ¬
    -0.07
     ages
    -0.07
    fp
    -0.07
    Toe
    -0.06
    ul
    -0.06
    _REQUIRED
    -0.06
     ourselves
    -0.06
    POSITIVE LOGITS
     own
    0.14
     Own
    0.12
    own
    0.11
    Own
    0.11
     sendiri
    0.10
     propias
    0.10
    使èĩªå·±
    0.09
     OWN
    0.09
     selves
    0.09
     próprias
    0.09
    Activations Density 0.249%

    No Known Activations