© 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. 47445
    Prev
    Next
    INDEX
    Explanations

    contrasts, paved with

    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
    çľĭåĪ°è¿Ļ个
    -0.09
    äºĨè¿Ļ个
    -0.08
    æĶ¿éĥ¨
    -0.08
    äºĨè¿Ļä¸Ģ
    -0.08
    ÑĢид
    -0.08
    orton
    -0.07
    éĢļè¿ĩè¿Ļ个
    -0.07
    ä»İè¿Ļ个
    -0.07
    çļĦæŶåĢĻå°±
    -0.07
    çļĦè¿Ļ个
    -0.07
    POSITIVE LOGITS
    uos
    0.07
    uy
    0.07
    çĽ¸å¯¹åºĶçļĦ
    0.07
    ucch
    0.07
    ular
    0.06
     wiederum
    0.06
    å½ĵçĦ¶
    0.06
    ata
    0.06
    å°¾
    0.06
    ucs
    0.06
    Activations Density 0.325%

    No Known Activations