© 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. 61218
    Prev
    Next
    INDEX
    Explanations

    will proceed to recover

    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
    andin
    -0.07
    irit
    -0.07
    ois
    -0.07
    æĭĽ
    -0.06
    oord
    -0.06
    ध
    -0.06
    ||
    -0.06
    vy
    -0.06
    oh
    -0.06
     menun
    -0.06
    POSITIVE LOGITS
    åIJİç»ŃçļĦ
    0.08
     subsequently
    0.07
    åIJİç»Ń
    0.07
    acket
    0.07
    çĦ¶åIJİ
    0.07
    çĦ¶åIJİå°Ĩ
    0.07
     thereafter
    0.07
     proceed
    0.07
    åIJİæŀľ
    0.07
    æĹłæ¯Ķ
    0.07
    Activations Density 0.244%

    No Known Activations