© 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. 56942
    Prev
    Next
    INDEX
    Explanations

    male and female

    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
     approximation
    -0.07
    ä»
    -0.06
    ackbar
    -0.06
     compress
    -0.06
    aders
    -0.06
    olynomial
    -0.06
    Someone
    -0.06
     subrange
    -0.06
    ç£ħ
    -0.06
    å°½åı¯èĥ½åľ°
    -0.06
    POSITIVE LOGITS
     females
    0.11
     female
    0.11
    çĶ·æĢ§
    0.10
    emales
    0.10
    女æĢ§
    0.10
     male
    0.10
    çĶ·æĢ§çļĦ
    0.09
    女çļĦ
    0.09
     Female
    0.09
    emale
    0.09
    Activations Density 0.003%

    No Known Activations