© 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. 18523
    Prev
    Next
    INDEX
    Explanations

    extruder, phone, system, robot

    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
    dcc
    -0.08
    öch
    -0.08
    undi
    -0.08
    çľĭä¸Ń
    -0.07
    åį´è®©
    -0.07
    æĺ¯å±ŀäºİ
    -0.07
    è¿ĺä¸įåĪ°
    -0.07
    lick
    -0.07
    imson
    -0.07
    &t
    -0.07
    POSITIVE LOGITS
    çĶ±æѤ
    0.08
    ä¹Łè¦ģ
    0.07
    ä¹Łåħ·æľī
    0.06
    á»ĭ
    0.06
    ä¹Łå¿ħé¡»
    0.06
    à®Łà¯Ī
    0.06
    -imm
    0.06
    Ital
    0.06
    ahari
    0.06
     Squad
    0.06
    Activations Density 0.024%

    No Known Activations