© 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. 15075
    Prev
    Next
    INDEX
    Explanations

    conjunctions indicating consequence

    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
    éĤ£
    -0.08
    æ·ij
    -0.07
     Means
    -0.06
    ধà§įয
    -0.06
    èķ
    -0.06
    ats
    -0.06
    emas
    -0.06
    åı¯èĥ½åıijçĶŁ
    -0.06
    éĢĤåIJĪçļĦ
    -0.06
    åı¯èĥ½
    -0.06
    POSITIVE LOGITS
    empio
    0.08
    ificación
    0.08
    Ø´ÙĨ
    0.08
    onn
    0.07
    lish
    0.07
    à¸Ĺีà¹Ģà¸Ķียว
    0.07
    æĥ¦è®°
    0.07
    çī¹å°Ķ
    0.07
    stery
    0.07
    åıĭæĥħéĵ¾æİ¥
    0.07
    Activations Density 0.014%

    No Known Activations