© 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. 64207
    Prev
    Next
    INDEX
    Explanations

    collect the terms in

    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
    ÙĤÙĩ
    -0.08
    loff
    -0.08
    çݺ
    -0.07
    jach
    -0.07
    åĨ²çł´
    -0.07
    .cc
    -0.07
     cared
    -0.06
    empat
    -0.06
     coded
    -0.06
    -ci
    -0.06
    POSITIVE LOGITS
    éb
    0.08
    obile
    0.07
    also
    0.07
    åijľ
    0.07
    çĥ¤é±¼
    0.07
    rov
    0.07
     inbound
    0.07
    дÑĭÒĽ
    0.07
    ãm
    0.07
    zl
    0.06
    Activations Density 0.343%

    No Known Activations