© 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. 44090
    Prev
    Next
    INDEX
    Explanations

    there exists

    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
    umon
    -0.08
    ifestyles
    -0.07
    oubl
    -0.07
    oyer
    -0.07
    æĺİç¡®äºĨ
    -0.07
    éģĹçķĻ
    -0.07
    _None
    -0.06
    åĪĿæľŁ
    -0.06
    .strict
    -0.06
    gy
    -0.06
    POSITIVE LOGITS
    è¾Ħ
    0.08
    ä¸İä¹ĭ
    0.08
    缸åºĶçļĦ
    0.08
    çĽ¸å¯¹åºĶçļĦ
    0.08
     corresponding
    0.08
    ãģļãģ¤
    0.07
    å¿ħãģļ
    0.07
     dagegen
    0.07
    缸æĩī
    0.07
    ardia
    0.07
    Activations Density 0.005%

    No Known Activations