© 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. 42370
    Prev
    Next
    INDEX
    Explanations

    vectors represented by indices like 'n' or 'N'

    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
    pon
    -0.08
    loge
    -0.07
    overs
    -0.06
    -driver
    -0.06
    ivery
    -0.06
    illante
    -0.06
    sted
    -0.06
     enf
    -0.06
    è½
    -0.06
    被æĴŀ
    -0.06
    POSITIVE LOGITS
    åģĩ
    0.08
    SOAP
    0.08
     Morm
    0.08
    azzi
    0.08
    å¤ļèĬ¬
    0.08
    å°ijä¸įäºĨ
    0.08
    æĸĩæijĺ
    0.08
    [âĢ¦
    0.07
    ickl
    0.07
    大å®Ŀ
    0.07
    Activations Density 0.117%

    No Known Activations