© 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. 26336
    Prev
    Next
    INDEX
    Explanations

    present disclosure

    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
    ä¼Ĺ
    -0.07
    ello
    -0.07
    opher
    -0.07
    æ°Ķ象åı°
    -0.07
    åħ¬çĦ¶
    -0.07
    éĤ
    -0.07
    ä¹±æĶ¾
    -0.07
    rosa
    -0.07
    urahan
    -0.06
    åįģåħ«æĿ¡
    -0.06
    POSITIVE LOGITS
    assem
    0.08
    幸äºı
    0.08
    deles
    0.07
    åĨĻä¸Ģç¯ĩ
    0.07
    —.
    0.07
    ×Ķ׾
    0.06
    éģµä»İ
    0.06
    ãĥģãĥ£ãĥ³
    0.06
    **—
    0.06
     попÑĢ
    0.06
    Activations Density 0.018%

    No Known Activations