© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48168
    Prev
    Next
    INDEX
    Explanations

    "A" followed by explanation

    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
    abi
    -0.07
    lo
    -0.07
    ulette
    -0.07
    awas
    -0.07
    /locale
    -0.07
    èĮĤ
    -0.06
    _perc
    -0.06
    awa
    -0.06
    èĬ³èįī
    -0.06
    owe
    -0.06
    POSITIVE LOGITS
    ONSE
    0.07
    laki
    0.07
    rena
    0.07
    åѦæ³ķ
    0.07
    zza
    0.07
    scheid
    0.07
    [text
    0.07
    è¿ĺ表示
    0.07
    à¸ģà¸ĩ
    0.07
    åľ°ä¹ħ
    0.06
    Activations Density 0.024%

    No Known Activations