© 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. 33700
    Prev
    Next
    INDEX
    Explanations

    point guard, variety hits, first EF, tonka, wide area, day, right guard, middle dot, pales, influencing

    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
    udou
    -0.08
    apons
    -0.08
    empre
    -0.08
    è§ģäºĨ
    -0.08
    racia
    -0.08
    passen
    -0.07
    trer
    -0.07
     conseille
    -0.07
    è®¤è®¤çľŁ
    -0.07
    ocop
    -0.07
    POSITIVE LOGITS
    å½¹
    0.07
    itorial
    0.07
    use
    0.07
    isc
    0.07
    /
    0.06
    ino
    0.06
    åĿŀ
    0.06
    c
    0.06
    ilog
    0.06
    iment
    0.06
    Activations Density 0.925%

    No Known Activations