© 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. 44943
    Prev
    Next
    INDEX
    Explanations

    mathematical identity elements

    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
    agrid
    -0.09
    为好åıĭ
    -0.08
    eus
    -0.08
    gorm
    -0.08
    renc
    -0.08
    _DEPRECATED
    -0.08
    åīį身
    -0.08
    _REQUIRE
    -0.07
    _NUMERIC
    -0.07
    ferred
    -0.07
    POSITIVE LOGITS
    ç²ĺåľŁ
    0.08
    ither
    0.07
    ä»»ä½ķ
    0.07
    ç«ł
    0.06
    å°½äºĨ
    0.06
    å°½
    0.06
    ä¸ĩçī©
    0.06
     kiri
    0.06
    åľ¨ä»»ä½ķ
    0.06
    è°ģéĥ½
    0.06
    Activations Density 0.005%

    No Known Activations