© 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. 49825
    Prev
    Next
    INDEX
    Explanations

    liquid refrigerant

    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
    éģĩè§ģä½ł
    -0.07
    enni
    -0.07
    äºĴèģĶ
    -0.07
    enho
    -0.07
    çĤ¹èĩ³
    -0.06
    驾
    -0.06
    EME
    -0.06
    ä¸Ģç»ıåıijçİ°
    -0.06
    ä½įéĿ¢
    -0.06
    æĭĹ
    -0.06
    POSITIVE LOGITS
    strup
    0.10
    illy
    0.08
    éĴŁå£°
    0.07
    æŃ¤èµ·
    0.07
    æѤ
    0.07
    staan
    0.07
    æľīæľŁå¾ĴåĪij
    0.07
    warts
    0.07
    è°IJ
    0.07
    ewire
    0.07
    Activations Density 0.019%

    No Known Activations