© 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. 41354
    Prev
    Next
    INDEX
    Explanations

    mentioning or referencing information

    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
    ilog
    -0.07
    oteric
    -0.07
     ÏĢά
    -0.07
    大鱼
    -0.06
    ces
    -0.06
    rena
    -0.06
    ogram
    -0.06
    éĢ£ä¼ij
    -0.06
     supposedly
    -0.06
    çŃīä¼Ĺå¤ļ
    -0.06
    POSITIVE LOGITS
     optional
    0.10
     briefly
    0.10
     mention
    0.09
    ä¸Ģ并
    0.09
    çĤ¹åĪ°
    0.09
     brief
    0.08
     mentions
    0.08
     ìĸ¸ê¸ī
    0.08
    è¿Ļä¸ĢçĤ¹
    0.08
    ç®Ģè¦ģ
    0.08
    Activations Density 0.023%

    No Known Activations