© 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. 12020
    Prev
    Next
    INDEX
    Explanations

    parentheses followed by equals

    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
    <|fim_suffix|>
    -0.08
    æĶ¶èµ·åĽŀå¤į
    -0.06
     ãĤ¹ãĥĿãĥ³ãĤµãĥ¼ãĤµãĤ¤ãĥĪ
    -0.06
     Decompiled
    -0.06
     borg
    -0.06
    полÑĮ
    -0.06
    <\/
    -0.06
     bât
    -0.06
    ÙĨÙģ
    -0.06
    Å©ng
    -0.06
    POSITIVE LOGITS
    æľĢæĸ°åıijå¸ĥ
    0.06
    krim
    0.06
    uko
    0.06
    <|im_start|>
    0.06
    phu
    0.06
    gena
    0.06
    HEMA
    0.05
    JsonValue
    0.05
     __
    0.05
    "She
    0.05
    Activations Density 0.022%

    No Known Activations