© 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. 14127
    Prev
    Next
    INDEX
    Explanations

    coherent, rigid, active, biased

    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
    ��
    -0.06
    èĪįåĪ©
    -0.06
    _replace
    -0.06
    ���
    -0.06
    缸è§ģ
    -0.06
    åŀ¢
    -0.06
    èĥ¶åİŁ
    -0.06
    ר×ĺ
    -0.06
    è¿«
    -0.06
    uro
    -0.06
    POSITIVE LOGITS
    顾åIJįæĢĿä¹ī
    0.09
    olim
    0.08
    IZED
    0.08
    ä½ľåĪĻ
    0.08
    çīĪæľ¬çļĦ
    0.07
    ä¸ĸçķĮéĩĮ
    0.07
    åĪĨæŶ
    0.07
    imei
    0.07
    OLUM
    0.07
    leston
    0.07
    Activations Density 0.029%

    No Known Activations