© 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. 19137
    Prev
    Next
    INDEX
    Explanations

    I have

    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
    åħ¬åı¸è§Ħ模
    -0.08
     metav
    -0.08
    TED
    -0.07
    欢è¿İåIJĦä½į
    -0.07
    éļıåľ°
    -0.07
    /max
    -0.07
    çĺª
    -0.07
     Fuss
    -0.07
    çĶļèĢħ
    -0.07
     preoc
    -0.06
    POSITIVE LOGITS
     Fate
    0.07
    .Requires
    0.07
    å¤ļåĬŁèĥ½
    0.07
    æ¦ľ
    0.07
    uri
    0.07
    Cole
    0.06
    åīį身
    0.06
    ariat
    0.06
     Cole
    0.06
    _asm
    0.06
    Activations Density 0.001%

    No Known Activations