© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 62844
    Prev
    Next
    INDEX
    Explanations

    numbers followed by specific 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
    ccione
    -0.08
    ekar
    -0.07
    EMA
    -0.07
    çIJħçIJĬ
    -0.07
    anny
    -0.07
    çķĻæģĭ
    -0.07
    åĴĮæĻºæħ§
    -0.07
    θεν
    -0.07
     prevailing
    -0.07
    Monster
    -0.07
    POSITIVE LOGITS
     psz
    0.07
    åĪĨç±»åı·
    0.07
    fatt
    0.07
     altrett
    0.06
    SPATH
    0.06
    agul
    0.06
    åľ©
    0.06
    ä¹İ
    0.06
    ä¸įæŃ»
    0.06
    æ´»åĮĸ
    0.06
    Activations Density 0.013%

    No Known Activations