© 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. 16510
    Prev
    Next
    INDEX
    Explanations

    numbers and code syntax

    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
     Allem
    -0.08
    çĥŃçĥĪç¥Ŀè´º
    -0.08
    éģµçºª
    -0.08
    ivin
    -0.07
    _RELEASE
    -0.07
    åij¨åĪĬ
    -0.07
    ãĤ¤ãĥī
    -0.07
    åħļç»Ħ
    -0.07
    áf
    -0.07
    _generic
    -0.07
    POSITIVE LOGITS
     exponent
    0.08
    èĬ½
    0.07
    礼
    0.07
    级
    0.07
    -level
    0.07
    å±Ĥ次
    0.07
    mani
    0.07
    =log
    0.07
    ç´ļ
    0.06
    ÑĬл
    0.06
    Activations Density 0.010%

    No Known Activations