© 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. 1820
    Prev
    Next
    INDEX
    Explanations

    continuous action or state

    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
    å·²ä¹ħçļĦ
    -0.09
    å·²ä¹ħ
    -0.08
    ç«ĭåį³è´Ńä¹°
    -0.08
    icer
    -0.08
    å¾Īä¹ħäºĨ
    -0.08
    ä¸Ģå¤ľ
    -0.08
    åĪĿæŃ¥
    -0.08
    ä¸ĢåĪĩéĥ½
    -0.07
    åħ¨éĿ¢äºĨ解
    -0.07
     ebenfalls
    -0.07
    POSITIVE LOGITS
    ìĶ©
    0.11
    åıªè¦ģä¸Ģ
    0.10
    åį´å§ĭç»Ī
    0.10
    ä¸įæĸŃåľ°
    0.10
     câte
    0.09
    ä¸įæĸŃçļĦ
    0.09
    个ä¸įåģľ
    0.09
    ä¸į离
    0.09
    ãģļãģ¤
    0.08
    ä¸įåģľçļĦ
    0.08
    Activations Density 0.541%

    No Known Activations