© 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. 46616
    Prev
    Next
    INDEX
    Explanations

    words separated by punctuation

    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
    ').'</
    -0.08
    íĦ±
    -0.07
    åĺ²
    -0.07
    åľ¨å¿ħ
    -0.07
    kop
    -0.07
    jat
    -0.07
    çĪĨäºĨ
    -0.07
    åĮĸå·¥åİĤ
    -0.07
    obuf
    -0.07
    lemi
    -0.07
    POSITIVE LOGITS
     [âĢ¦]
    0.11
    Âł
    0.08
     [...]
    0.08
    âĢ¦
    0.08
     âĢ¦
    0.08
     [âĢ¦
    0.07
    0.07
     ...
    0.07
    ...
    0.07
    ____
    0.07
    Activations Density 0.440%

    No Known Activations