© 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. 1014
    Prev
    Next
    INDEX
    Explanations

    software distributed

    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
    .ssl
    -0.07
    è¯Ħè®®
    -0.07
    AtPath
    -0.07
    AGENT
    -0.07
    åĮħæĭ¬äºĨ
    -0.07
    TagName
    -0.07
    /tutorial
    -0.07
    	RETURN
    -0.07
    ä¸ĵä¸ļæĢ§
    -0.06
    ,DB
    -0.06
    POSITIVE LOGITS
    asters
    0.07
    umph
    0.07
    ales
    0.07
    aston
    0.06
    rove
    0.06
    è§Ĥ念
    0.06
    anten
    0.06
    antom
    0.06
    rosis
    0.06
    éĶĢ
    0.06
    Activations Density 0.005%

    No Known Activations