© 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. 23822
    Prev
    Next
    INDEX
    Explanations

    every/each x, x other

    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
    åį«åĽ½
    -0.07
     proprietor
    -0.07
    landen
    -0.07
    ieszcz
    -0.06
    Ren
    -0.06
    _only
    -0.06
    imar
    -0.06
    leos
    -0.06
     Semaphore
    -0.06
    Subset
    -0.06
    POSITIVE LOGITS
     thêm
    0.10
    è¶Ĭ
    0.09
    ë§Īëĭ¤
    0.09
     added
    0.08
    _added
    0.08
    大麦
    0.08
    ucas
    0.07
     adds
    0.07
     increase
    0.07
    each
    0.07
    Activations Density 0.033%

    No Known Activations