© 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. 56688
    Prev
    Next
    INDEX
    Explanations

    func 2, test ();

    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
    æ±Łå¤ı
    -0.07
    erg
    -0.06
    fal
    -0.06
    æŃ¥åħ¥
    -0.06
    éªı
    -0.06
    um
    -0.06
    w
    -0.05
    å¡«
    -0.05
    aming
    -0.05
    ier
    -0.05
    POSITIVE LOGITS
    пей
    0.08
    adata
    0.08
    åıĸå¾Ĺæĸ°
    0.08
    ExecutionContext
    0.08
    permalink
    0.08
    _refs
    0.07
    ãĥĭãĥĥãĤ¯
    0.07
    нÑĸка
    0.07
    λοÏį
    0.07
    æĹ©æĬ¥
    0.07
    Activations Density 0.028%

    No Known Activations