© 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. 40201
    Prev
    Next
    INDEX
    Explanations

    to followed by a verb

    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
    entially
    -0.08
    亦çĦ¶
    -0.07
    umably
    -0.07
    alkan
    -0.07
    ients
    -0.07
    asm
    -0.07
    unist
    -0.07
    lz
    -0.07
    ãĢħ
    -0.07
    onomia
    -0.07
    POSITIVE LOGITS
    reme
    0.08
    çŁ¥éģĵæĪij
    0.08
    Ñģл
    0.08
    çŁ¥éģĵä½ł
    0.08
    çŁ¥éģĵä»ĸ
    0.07
    æ§ĥ
    0.07
    æ¯Ķè¾ĥéķ¿
    0.07
    สิà¸ķ
    0.07
    è¿ĩ人
    0.07
    æ¯Ķè¾ĥå°ı
    0.06
    Activations Density 0.220%

    No Known Activations