© 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. 50494
    Prev
    Next
    INDEX
    Explanations

    el or ie endings, bon, ham, etti, URO

    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
    ihad
    -0.06
    äºİè¡Į
    -0.06
    èĤ¡
    -0.06
    ä¸İçĶŁæ´»
    -0.06
    æijĴ
    -0.06
    çĹĽå¿«
    -0.06
    icans
    -0.06
    Ń
    -0.06
    .Authentication
    -0.05
     Prensa
    -0.05
    POSITIVE LOGITS
    pta
    0.08
     herself
    0.08
    -sama
    0.08
    åIJĽå®ī
    0.08
    ombang
    0.07
    .fromCharCode
    0.07
    ughs
    0.07
    lili
    0.07
    idang
    0.07
    anee
    0.07
    Activations Density 0.644%

    No Known Activations