© 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. 11956
    Prev
    Next
    INDEX
    Explanations

    metal compounds and alloys

    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
    ksam
    -0.07
    já
    -0.07
     Mons
    -0.07
    ä½İèIJ½
    -0.06
     Radio
    -0.06
    åĩºå¤Ħ
    -0.06
    æ§Ľ
    -0.06
    Ellipse
    -0.06
     radio
    -0.06
    azen
    -0.06
    POSITIVE LOGITS
    timb
    0.08
    å°ĸ
    0.08
    EDIA
    0.08
    creation
    0.08
    ç»ĵæĻ¶
    0.08
    quettes
    0.08
     formation
    0.07
    ync
    0.07
    semble
    0.07
    FileSync
    0.07
    Activations Density 0.010%

    No Known Activations