© 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. 18826
    Prev
    Next
    INDEX
    Explanations

    use to describe actions or instructions

    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
    ä½ĨéĤ£
    -0.08
    å¸ĮæľĽå¯¹æĤ¨
    -0.07
    åį´ä¸įçŁ¥éģĵ
    -0.07
    éĤ£ä¸įæĺ¯
    -0.07
    late
    -0.07
    ä¸Ģç½ij
    -0.07
    就没
    -0.06
    ker
    -0.06
    æľĢæĸ°è¯Ħ论
    -0.06
    éĤ£çīĩ
    -0.06
    POSITIVE LOGITS
    è¿Ļä¸ĢæŃ¥
    0.12
    .Then
    0.08
    atha
    0.08
    sume
    0.07
    ä¸įæĥĬ
    0.07
    !),
    0.07
    aso
    0.07
    äºİæѤ
    0.07
    ectl
    0.07
    çĶŁäº§è½¦éĹ´
    0.07
    Activations Density 0.335%

    No Known Activations