© 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. 21426
    Prev
    Next
    INDEX
    Explanations

    override method definitions

    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
    äºİ人
    -0.08
    ieza
    -0.08
    èĪ¬åľ°
    -0.07
    nico
    -0.07
    æĢ§åľ°
    -0.07
    æĹłè·¯
    -0.07
    idata
    -0.07
    виÑĩ
    -0.07
    ÅĽciÄħ
    -0.07
    ahoo
    -0.07
    POSITIVE LOGITS
    ↵
    0.07
    ï¼Į
    0.07
    ente
    0.07
    imb
    0.07
    erk
    0.06
    ucken
    0.06
    æ¦Ħ
    0.06
    adel
    0.06
    orre
    0.06
    ryn
    0.06
    Activations Density 0.045%

    No Known Activations