© 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. 47030
    Prev
    Next
    INDEX
    Explanations

    date separators

    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
    affle
    -0.08
    ela
    -0.07
     |:
    -0.07
    ung
    -0.07
    esse
    -0.07
    ambil
    -0.07
    <*
    -0.06
    áĥķáĥĶáĥľ
    -0.06
     Bent
    -0.06
    é²ľæĺİ
    -0.06
    POSITIVE LOGITS
    溪éķĩ
    0.07
    çŃīå¾ħçĿĢ
    0.07
    çİī
    0.07
    ÙĪاÙħ
    0.06
    LOCKS
    0.06
     Pah
    0.06
    scher
    0.06
    å°Ķåħĭ
    0.06
    èĥĨåŃIJ
    0.06
    otec
    0.06
    Activations Density 0.029%

    No Known Activations