© 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. 39210
    Prev
    Next
    INDEX
    Explanations

    interest and related words

    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
    elijkse
    -0.09
    earer
    -0.09
    emento
    -0.09
    jure
    -0.08
    gestellt
    -0.08
    sweise
    -0.08
    osing
    -0.07
    Ø´ÙĬØ©
    -0.07
    ÄŁan
    -0.07
    onical
    -0.07
    POSITIVE LOGITS
    पà¥Ĥरà¥įण
    0.10
    çĽİçĦ¶
    0.09
    Ī
    0.08
    ampo
    0.08
    ìĹī
    0.08
    åĴĮèĥ½åĬĽ
    0.08
    باÙĩ
    0.08
    nahme
    0.07
    åľ¨äºİ
    0.07
    entif
    0.07
    Activations Density 0.040%

    No Known Activations