© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 62454
    Prev
    Next
    INDEX
    Explanations

    evidence of work or success

    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
    har
    -0.07
    ä¸ĭéĿ¢å°ıç¼ĸ
    -0.07
    μαÏĦο
    -0.07
    æļĸæĦı
    -0.07
    çĪ±ç¾İ
    -0.07
    ÑĢоки
    -0.07
     Charter
    -0.07
    ripe
    -0.06
    رد
    -0.06
    adm
    -0.06
    POSITIVE LOGITS
    çĶ·
    0.07
    iot
    0.07
    aml
    0.07
    uko
    0.07
    zej
    0.07
    dain
    0.07
    änden
    0.07
    kit
    0.07
    bog
    0.06
    arn
    0.06
    Activations Density 0.039%

    No Known Activations