© 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. 9240
    Prev
    Next
    INDEX
    Explanations

    material and layer structures

    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
     NotImplemented
    -0.08
    olari
    -0.07
    ModuleName
    -0.07
     competitiveness
    -0.07
    orest
    -0.07
     Modular
    -0.07
    å½ĵå¹´çļĦ
    -0.07
    estre
    -0.07
    éģİå¾Ģ
    -0.07
    .fx
    -0.07
    POSITIVE LOGITS
    åħ¶éĹ´
    0.09
    åĨħéĥ¨
    0.08
    åĨħçļĦ
    0.08
     interior
    0.08
    hom
    0.08
    åħ§éĥ¨
    0.08
     medium
    0.08
     interiors
    0.07
    åĨħè¿Ľè¡Į
    0.07
    æ·±å¤Ħ
    0.07
    Activations Density 0.020%

    No Known Activations