© 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. 24907
    Prev
    Next
    INDEX
    Explanations

    numbers followed by dots and citations

    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
    æĥij
    -0.07
    orsa
    -0.06
    EMS
    -0.06
    ?]
    -0.06
    åĪ»
    -0.06
    åĨľä¸ļæľºæ¢°
    -0.06
    å°Ĩè¿Ļ
    -0.06
    ultip
    -0.06
    staticmethod
    -0.06
    æĽ¿
    -0.06
    POSITIVE LOGITS
     insp
    0.08
    æĿŀ
    0.08
    amil
    0.08
    è¯¥ä½ľèĢħ
    0.07
    yé
    0.07
    æĪªæŃ¢åĪ°
    0.07
    alj
    0.07
    INGER
    0.07
    æ´»ä¸ĭåİ»
    0.07
    à¸ļุรี
    0.07
    Activations Density 0.040%

    No Known Activations