© 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. 2675
    Prev
    Next
    INDEX
    Explanations

    sulfides, sulfates, oxides, chlorides, silicides

    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
    åĪ°ä½į
    -0.06
    nosti
    -0.06
     mini
    -0.06
    itaal
    -0.06
    Mini
    -0.06
    1
    -0.06
     lodash
    -0.06
    èŃ
    -0.05
    åĨį说
    -0.05
    zur
    -0.05
    POSITIVE LOGITS
    atea
    0.09
    trice
    0.09
     thereof
    0.08
    èĬĤåIJİ
    0.08
    ä¸Ńéĵģ
    0.08
    åIJĦè¡Įä¸ļ
    0.08
    约车
    0.08
    å¤į
    0.08
    hent
    0.08
    κλο
    0.08
    Activations Density 0.066%

    No Known Activations