© 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. 16578
    Prev
    Next
    INDEX
    Explanations

    "i" followed by specific tokens

    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
    ranken
    -0.09
    ånd
    -0.08
    apesh
    -0.08
    ì²Ń
    -0.08
    ëĭĪëĭ¤
    -0.08
    ivalente
    -0.08
    çĦ¶åIJİåıĪ
    -0.08
    ÑģÑĤÑĢе
    -0.07
    аннÑı
    -0.07
    accia
    -0.07
    POSITIVE LOGITS
    åľ¨ä¸Ĭè¿°
    0.06
    0.06
     afer
    0.06
    ¯¯
    0.06
    åħ¢åħ¢ä¸ļä¸ļ
    0.06
    以德
    0.06
    i
    0.06
    ilst
    0.06
    ีà¹Ī
    0.06
    Ø´ÙĬØ©
    0.06
    Activations Density 0.051%

    No Known Activations