© 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. 21802
    Prev
    Next
    INDEX
    Explanations

    residue analysis and positions

    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
    /we
    -0.08
    缸è¾ħ缸æĪIJ
    -0.07
    ision
    -0.07
    strlen
    -0.07
    .rstrip
    -0.07
    ÑĥÑģка
    -0.07
    asta
    -0.07
    memb
    -0.07
    (strlen
    -0.07
    çĶļèĩ³æľīäºĽ
    -0.07
    POSITIVE LOGITS
    ]=$
    0.06
    èĹ
    0.06
    _ls
    0.06
    erÃŃa
    0.06
    .calls
    0.06
    大æĪ·
    0.06
    inna
    0.06
    éĤ£åı¯
    0.06
    æ¸Ĭ
    0.06
     coder
    0.06
    Activations Density 0.002%

    No Known Activations