© 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. 49294
    Prev
    Next
    INDEX
    Explanations

    technical coding and development

    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
    inas
    -0.08
    onar
    -0.08
    æļ¨
    -0.08
    åıĬè¦ģæ±Ĥ
    -0.07
    eck
    -0.07
    antar
    -0.07
    LOTS
    -0.07
    ebin
    -0.07
    èĦĪ
    -0.07
    èĻ½çĦ¶æĪij们
    -0.07
    POSITIVE LOGITS
     nên
    0.09
     anyway
    0.09
    ãģªãģĦãģ®ãģ§
    0.08
    åĽłæѤ
    0.08
     anyways
    0.08
     donc
    0.08
     joten
    0.07
    ikov
    0.07
    ãģ§ãģįãĤĭãģ®ãģ§
    0.07
    ãģĹãģ¦ãģĦãĤĭãģ®ãģ§
    0.07
    Activations Density 0.013%

    No Known Activations