© 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. 23681
    Prev
    Next
    INDEX
    Explanations

    Compiler, register, Manufacturer, candidate

    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
    æķĮ
    -0.06
    xba
    -0.06
    MI
    -0.06
    缪
    -0.06
    ä¸ĸ家
    -0.06
     MIL
    -0.05
    è¿Ļç§įåģļæ³ķ
    -0.05
    å¶
    -0.05
    åıįåĩ»
    -0.05
    ä¹īåĭĩ
    -0.05
    POSITIVE LOGITS
    à¹Ħมà¹Īà¸Ńย
    0.09
    ocache
    0.08
    elpers
    0.08
    è·¯éĢı
    0.08
    anyol
    0.07
    esting
    0.07
    apiers
    0.07
    recision
    0.07
    ARS
    0.07
    atatype
    0.07
    Activations Density 0.005%

    No Known Activations