© 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. 17390
    Prev
    Next
    INDEX
    Explanations

    check button

    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
    /manage
    -0.08
    ä¸Ń寻æī¾
    -0.08
    eneur
    -0.07
    poke
    -0.07
    åıĭ
    -0.07
    cip
    -0.07
    emor
    -0.07
    amble
    -0.07
    cian
    -0.07
    ')}}
    -0.07
    POSITIVE LOGITS
    ä¸įä¼ļå½±åĵį
    0.08
    à¸Ĺำà¹ĥหà¹īà¹Ģà¸ģิà¸Ķ
    0.08
    ä¼ļ导èĩ´
    0.07
    egro
    0.07
     yields
    0.07
    å°Ĩ使
    0.07
    ä¸įè°ĥ
    0.06
    à¸Ĺำà¹ĥหà¹ī
    0.06
    精彩åĨħ容
    0.06
    ä¼ļ使
    0.06
    Activations Density 0.070%

    No Known Activations