© 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. 29094
    Prev
    Next
    INDEX
    Explanations

    python/java/gradle configuration files

    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
    åħ°è¾¾
    -0.07
    èĤĺ
    -0.07
    ény
    -0.07
    èt
    -0.07
    inson
    -0.07
    _logits
    -0.07
    èm
    -0.07
    alink
    -0.06
    aid
    -0.06
    à¹Īาà¸ĩ
    -0.06
    POSITIVE LOGITS
    Builders
    0.07
    ixo
    0.07
    åį·åŃIJ
    0.07
    两端
    0.07
    éĺ
    0.06
     reopen
    0.06
    eux
    0.06
    ORLD
    0.06
    -cookie
    0.06
     getUsername
    0.06
    Activations Density 0.111%

    No Known Activations