© 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. 30634
    Prev
    Next
    INDEX
    Explanations

    alignment and centering

    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
    çķĻå®Ī
    -0.08
    ipay
    -0.07
    andes
    -0.07
    ÃŃn
    -0.07
    quip
    -0.07
    /send
    -0.07
    -Oct
    -0.07
    .prob
    -0.07
    biot
    -0.07
    ëŀ«
    -0.07
    POSITIVE LOGITS
    åıijå±ķä¸Ńå¿ĥ
    0.07
     palindrome
    0.07
    ALIGN
    0.07
     cent
    0.07
     extent
    0.07
     bloss
    0.07
     centered
    0.07
    extent
    0.06
     controlled
    0.06
    _extent
    0.06
    Activations Density 0.001%

    No Known Activations