© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 42286
    Prev
    Next
    INDEX
    Explanations

    characteristic polynomial, function, impedance, spectrum

    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
    s
    -0.07
    ugno
    -0.07
    ifice
    -0.07
    çĶ¨å®Į
    -0.07
    ora
    -0.07
     "=",
    -0.07
    ×Ļ×Ŀ
    -0.07
    ιδ
    -0.07
    zyma
    -0.07
    .LayoutParams
    -0.07
    POSITIVE LOGITS
    jenigen
    0.08
    à¸ģารà¸Ĺà¹Īà¸Ńà¸ĩà¹Ģà¸Ĺีà¹Īยว
    0.07
    nese
    0.07
    OnClick
    0.07
    çĶ±ä¹Ļæĸ¹
    0.07
    åħ¨å®¶
    0.06
    寸
    0.06
    ׾×ĺ
    0.06
    INAN
    0.06
    ván
    0.06
    Activations Density 0.012%

    No Known Activations