© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17702
    Prev
    Next
    INDEX
    Explanations

    null pointer, null hypothesis, null values

    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
    ekan
    -0.10
    elor
    -0.10
    althy
    -0.10
    Ö¼
    -0.09
    venz
    -0.09
    autiful
    -0.09
     Ranh
    -0.08
    ezz
    -0.08
    ëł¹
    -0.08
    attet
    -0.08
    POSITIVE LOGITS
    s
    0.11
    p
    0.09
    l
    0.09
    c
    0.09
    t
    0.09
    istic
    0.08
    ish
    0.08
    ness
    0.08
    k
    0.08
    åĻľ
    0.08
    Activations Density 0.034%

    No Known Activations