© 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. 61165
    Prev
    Next
    INDEX
    Explanations

    son, mother, former

    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
    çĽĸ
    -0.07
    asive
    -0.07
    eo
    -0.07
    èĢĮæĺ¯åĽłä¸º
    -0.06
    si
    -0.06
    alik
    -0.06
    uhn
    -0.06
    gy
    -0.06
    ollow
    -0.06
    ÑĤим
    -0.06
    POSITIVE LOGITS
    ibo
    0.08
    å¹Į
    0.08
     rootNode
    0.07
    .result
    0.07
    ParameterValue
    0.07
     Pekan
    0.07
    å®Ľ
    0.07
     reve
    0.07
    æŀľ
    0.07
    æĹ¥åĪ¶
    0.07
    Activations Density 0.091%

    No Known Activations