© 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. 29537
    Prev
    Next
    INDEX
    Explanations

    being alone or by oneself

    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
    ötz
    -0.08
     Muda
    -0.08
    á»ĥn
    -0.07
    ãĥ¼ãĥĦ
    -0.07
    kennt
    -0.07
    ä¸įæģ¯
    -0.07
    Ken
    -0.07
     übere
    -0.07
    è¿ģ
    -0.07
     collectively
    -0.06
    POSITIVE LOGITS
    çĭ¬
    0.21
    çį¨
    0.19
    åѤçĭ¬
    0.18
    çĭ¬å¤Ħ
    0.18
    åѤ
    0.17
    åѤçĭ¬çļĦ
    0.17
    çĭ¬è¡Į
    0.17
    åѤåįķ
    0.17
    çĭ¬èĩª
    0.17
     solitary
    0.17
    Activations Density 0.079%

    No Known Activations