© 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. 16449
    Prev
    Next
    INDEX
    Explanations

    serializedVersion

    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
    andal
    -0.06
    ỡ
    -0.06
    åĪĩåħ¥
    -0.06
     README
    -0.06
    frey
    -0.06
    ipur
    -0.06
     Dagger
    -0.06
    å±ħåīį
    -0.06
    .axes
    -0.06
    èĥĮéĿł
    -0.06
    POSITIVE LOGITS
    æ®ī
    0.07
    çŁ¥ä¹ĭ
    0.07
    ÙĪتÙĬÙĨ
    0.07
    ACH
    0.07
    ç»ı管
    0.07
    ighting
    0.07
    éĺµ
    0.07
     serialVersionUID
    0.07
    à¸ķิ
    0.07
    "c
    0.07
    Activations Density 0.169%

    No Known Activations