© 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. 19923
    Prev
    Next
    INDEX
    Explanations

    defined variables and terms

    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
    以大
    -0.06
    :///
    -0.06
    ://{
    -0.06
    以æŃ¤ä¸º
    -0.06
    å°ĨæѤ
    -0.06
    åīįä¸Ģ
    -0.06
    å±±ä¹ĭ
    -0.06
    çĻ½éľ²
    -0.05
    Âł
    -0.05
    ////////////////////////////////////////////////////////////////////////////
    -0.05
    POSITIVE LOGITS
    ä¼łéĢĴæĽ´å¤ļä¿¡æģ¯
    0.08
    orsk
    0.08
    itek
    0.08
    cius
    0.08
    idou
    0.07
    _MISC
    0.07
    strom
    0.07
    ÙİاÙħ
    0.07
    gard
    0.07
     vs
    0.07
    Activations Density 0.010%

    No Known Activations