© 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. 12175
    Prev
    Next
    INDEX
    Explanations

    reporting statistical methods

    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
    araus
    -0.08
    çݩ家å°Ĩ
    -0.08
    详ç»Ĩåľ°åĿĢ
    -0.08
    ickness
    -0.07
    IDDLE
    -0.07
    /DTD
    -0.07
    InitStruct
    -0.07
     sanz
    -0.07
    æĬĺä¸įæī£
    -0.07
     substrate
    -0.07
    POSITIVE LOGITS
    åĩĨåĪĻ
    0.08
     misuse
    0.08
     reporting
    0.08
    ç¿°
    0.08
     ethical
    0.07
     ethics
    0.07
    å®īæħ°
    0.07
     decision
    0.07
     confidence
    0.07
    stat
    0.07
    Activations Density 0.053%

    No Known Activations