© 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. 34532
    Prev
    Next
    INDEX
    Explanations

    assumption or approximation

    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
     acum
    -0.08
    ÛĮشاÙĨ
    -0.08
     seman
    -0.07
    еÑģÑĤа
    -0.07
    umbu
    -0.07
     заÑĢегиÑģÑĤÑĢи
    -0.07
    çĿ£
    -0.07
    onex
    -0.07
    setw
    -0.07
     registered
    -0.07
    POSITIVE LOGITS
     assumptions
    0.17
     assumption
    0.17
     simpl
    0.11
     simplific
    0.10
     semplific
    0.10
    åģĩ设
    0.10
     assumed
    0.10
     Assumes
    0.10
    ç®ĢåĮĸ
    0.10
     assum
    0.10
    Activations Density 0.026%

    No Known Activations