© 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. 15800
    Prev
    Next
    INDEX
    Explanations

    legal and official roles

    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
    etet
    -0.08
    ÐijÐļ
    -0.08
    _SECURE
    -0.08
    è¦ģèµ°
    -0.08
    luck
    -0.08
     Pue
    -0.08
    æ²³éķĩ
    -0.07
    ++++++++
    -0.07
    VISION
    -0.07
    mania
    -0.07
    POSITIVE LOGITS
    宫
    0.07
    ä¸ºæľŁ
    0.07
    森
    0.06
    fter
    0.06
    çĺ
    0.06
    以ä¸ĭç®Ģ称
    0.06
    æĹ¥ä¸¾è¡Į
    0.06
    IDD
    0.06
     prer
    0.06
    por
    0.06
    Activations Density 0.082%

    No Known Activations