© 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. 8696
    Prev
    Next
    INDEX
    Explanations

    competing pathways

    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
     cant
    -0.07
    常çĶ¨
    -0.07
    yk
    -0.07
    меÑĤе
    -0.06
    å®īæİĴéĥ¨ç½²
    -0.06
    æľĢè¿ijæĽ´æĸ°
    -0.06
    åħ·ä½ĵæĥħåĨµ
    -0.06
    çĥģ
    -0.06
    æĪijä»¬çĽ¸ä¿¡
    -0.06
    æıŃ
    -0.06
    POSITIVE LOGITS
     indiscrim
    0.09
    ãģĽãģ£ãģĭãģı
    0.09
     overly
    0.08
    ä¸įæŃ¢
    0.08
    çļĦåħ¶ä»ĸ
    0.08
    ä¸įå¿ħè¦ģçļĦ
    0.08
    ãģĹãģ¦ãģĹãģ¾ãģĨ
    0.08
    ichel
    0.08
     prematurely
    0.08
    åıªé¡¾
    0.08
    Activations Density 0.019%

    No Known Activations