© 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. 13072
    Prev
    Next
    INDEX
    Explanations

    alternative options instead

    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
     inv
    -0.07
     based
    -0.07
    æĪijå¿ĥéĩĮ
    -0.07
    æł¹æį®åħ¬åı¸
    -0.07
    å°±æĺ¯ä»¥
    -0.06
    ÑĥÑħ
    -0.06
    ucha
    -0.06
    TestMethod
    -0.06
    ReturnValue
    -0.06
    bey
    -0.06
    POSITIVE LOGITS
    æĶ¹çĶ¨
    0.10
    çŃīåħ¶ä»ĸ
    0.09
    åľ¨åħ¶ä»ĸ
    0.09
    æĽ¿ä»£åĵģ
    0.08
    Alternative
    0.08
    æľīåħ¶ä»ĸ
    0.08
     alternatives
    0.08
     Alternative
    0.08
    instead
    0.08
     Altern
    0.08
    Activations Density 0.217%

    No Known Activations