© 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. 49384
    Prev
    Next
    INDEX
    Explanations

    also, similarly, well

    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
    ivel
    -0.08
    淮海
    -0.07
    bcd
    -0.06
    å¹´å§ĭ
    -0.06
    ayers
    -0.06
    æ¬Ħ
    -0.06
    åĭĩå¾Ģ缴åīį
    -0.06
    ursor
    -0.06
    ôm
    -0.06
    åıĪä¸į
    -0.06
    POSITIVE LOGITS
    éļıä¹ĭ
    0.10
    è·ŁçĿĢ
    0.08
    缸åºĶçļĦ
    0.08
    æľĢ好æĺ¯
    0.07
    éļıçĿĢ
    0.07
    edas
    0.07
    缸åºĶ
    0.07
    éģµ
    0.07
    è·ŁèijĹ
    0.07
    顺延
    0.07
    Activations Density 0.108%

    No Known Activations