© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 26916
    Prev
    Next
    INDEX
    Explanations

    age and gender description

    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
    åĪĨä¹ĭä¸Ģ
    -0.08
    ä¸į妨
    -0.08
    èĢIJå¿ĥçļĦ
    -0.08
     themselves
    -0.07
    åĪĨä¹ĭ
    -0.07
     sanction
    -0.07
    ä»ĸå¿ĥéĩĮ
    -0.07
    æĪijçļĦå¿ĥéĩĮ
    -0.06
    使å®ĥ
    -0.06
    æĻ¶èݹ
    -0.06
    POSITIVE LOGITS
    çļĦåŁºæľ¬æĥħåĨµ
    0.09
    ä¾ĭè¡Į
    0.08
    åķĨåĵģä¿¡æģ¯
    0.08
    身份信æģ¯
    0.08
     ages
    0.08
     routine
    0.08
    rego
    0.08
    çļĦåħ·ä½ĵæĥħåĨµ
    0.08
    说èĩªå·±
    0.08
    relu
    0.07
    Activations Density 0.411%

    No Known Activations