© 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. 48590
    Prev
    Next
    INDEX
    Explanations

    ancient history

    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
    ombra
    -0.07
    çŁ¾
    -0.07
    eln
    -0.07
    صار
    -0.07
    å¤§åľ£
    -0.07
    atholic
    -0.07
    éĺħ
    -0.07
     Virtu
    -0.07
    ilda
    -0.06
    çĤ¸å¼¹
    -0.06
    POSITIVE LOGITS
     primitive
    0.15
     Primitive
    0.13
    åİŁå§ĭçļĦ
    0.13
    åİŁå§ĭ
    0.13
     primit
    0.12
    primitive
    0.12
    åħ¬åħĥåīį
    0.12
     earliest
    0.12
    æ°ıæĹı
    0.12
    Proto
    0.11
    Activations Density 0.091%

    No Known Activations