© 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. 40636
    Prev
    Next
    INDEX
    Explanations

    electoral system, account fees, worker characteristics

    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
    åIJ«ç¬ij
    -0.08
    ACES
    -0.08
    ä¼ı
    -0.08
    æ´»
    -0.07
    æį·
    -0.07
     Lair
    -0.07
    夫åIJĽ
    -0.07
    éĥģ
    -0.07
    brig
    -0.07
    ä¼IJ
    -0.07
    POSITIVE LOGITS
    riter
    0.07
    ÏĢοι
    0.07
    çĶĺéľ²
    0.07
     ara
    0.07
    ader
    0.07
    大家éĥ½æĺ¯
    0.07
    ends
    0.07
    oa
    0.07
    èĩªè¾¾
    0.07
    æĬ¥å¤į
    0.07
    Activations Density 0.280%

    No Known Activations