© 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. 28231
    Prev
    Next
    INDEX
    Explanations

    financial service or legal issues

    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
    ergus
    -0.07
    NECT
    -0.07
    tig
    -0.07
    _guide
    -0.07
     namedtuple
    -0.07
    iler
    -0.06
    ç»ıæµİåľĪ
    -0.06
    è´¹çĶ¨çĶ±
    -0.06
    èĸªèµĦå¾ħéģĩ
    -0.06
    éĥ¨èIJ½
    -0.06
    POSITIVE LOGITS
    ymar
    0.08
    åį´ä¾ĿçĦ¶
    0.08
    èĦĤ
    0.07
    ãĥ©ãĥ«
    0.06
    æľĢåħ³éĶ®
    0.06
    Chance
    0.06
     vitt
    0.06
    boo
    0.06
    antas
    0.06
    طر
    0.06
    Activations Density 0.517%

    No Known Activations