© 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. 21456
    Prev
    Next
    INDEX
    Explanations

    field-driven, field dependence, field-induced

    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¶éģĵ
    -0.08
    æ¹ĸéĩĮ
    -0.07
    åħ°è¾¾
    -0.07
    ç©·
    -0.07
    ë²Į
    -0.07
    稽
    -0.07
     Scheda
    -0.07
    ãģıãģĦ
    -0.07
    emaine
    -0.07
    опеÑĢа
    -0.07
    POSITIVE LOGITS
     vector
    0.09
    vector
    0.09
    çŁ¢éĩı
    0.09
    bane
    0.08
    -vector
    0.08
     magnitude
    0.08
    强度
    0.08
    强度çļĦ
    0.08
     fields
    0.08
     vectors
    0.08
    Activations Density 0.002%

    No Known Activations