© 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. 57707
    Prev
    Next
    INDEX
    Explanations

    molecular weight

    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
    iros
    -0.08
     Pisa
    -0.07
    æľ¨å·¥
    -0.07
     Miser
    -0.07
    á»įt
    -0.07
    hone
    -0.07
    osaur
    -0.07
    orien
    -0.07
    à¹Ħม
    -0.07
    åĸ»
    -0.07
    POSITIVE LOGITS
    /ion
    0.07
    /gen
    0.06
    æį¢ç®Ĺ
    0.06
    ±
    0.06
    éĨ
    0.06
    umin
    0.06
    oi
    0.06
     Prepared
    0.06
    _tgt
    0.06
    erg
    0.06
    Activations Density 0.002%

    No Known Activations