© 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. 65076
    Prev
    Next
    INDEX
    Explanations

    null pointer or value

    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
    nict
    -0.07
    ool
    -0.06
    erven
    -0.06
    Earn
    -0.06
     Magn
    -0.06
    æĤł
    -0.06
    odon
    -0.06
    reverse
    -0.06
     modest
    -0.06
     dom
    -0.06
    POSITIVE LOGITS
    /null
    0.09
    ĥģ
    0.08
    空
    0.08
    пÑĥÑģÑĤ
    0.08
    __$
    0.08
    skip
    0.08
    _SKIP
    0.08
    imit
    0.07
    /false
    0.07
    /dis
    0.07
    Activations Density 0.004%

    No Known Activations