© 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. 40720
    Prev
    Next
    INDEX
    Explanations

    ell, ll, l followed by punctuation or specific suffixes

    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
    à§įত
    -0.09
    ়
    -0.08
    inig
    -0.08
    ezo
    -0.07
    à§įস
    -0.07
    chsel
    -0.07
    æĹłéĻħ
    -0.07
    äºĨä¸Ģå®ļ
    -0.07
    åī¯å±Ģéķ¿
    -0.07
     Ganze
    -0.07
    POSITIVE LOGITS
    halb
    0.10
    ï¸İ
    0.09
    ами
    0.09
    [email
    0.08
    ród
    0.08
    ç±
    0.08
    ÑĶÑĹ
    0.08
    tü
    0.07
    antic
    0.07
    utom
    0.07
    Activations Density 0.001%

    No Known Activations