© 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. 57046
    Prev
    Next
    INDEX
    Explanations

    Looking at the activations, all values are 0 in these examples. This neuron does not activate for any tokens in the provided documents. The neuron appears to find **nothing in these particular examples** (all activations are zero).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jrosseruk
    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
     “
    -0.09
    -0.08
    1
    -0.08
    2
    -0.08
     presently
    -0.08
     (
    -0.07
    “
    -0.07
     likewise
    -0.07
    0
    -0.07
     tiny
    -0.07
    POSITIVE LOGITS
    [".
    0.11
    ç¾İç¾İçļĦ
    0.10
    ä¸Ńå¿ĥç»Ħ
    0.10
     **âĢ¢
    0.10
    erenc
    0.09
    å®£ä¼łè´¯å½»
    0.09
    ä¹Łæľīä¸Ģå®ļçļĦ
    0.09
    ä½Ĩä¸įéĻIJäºİ
    0.09
    %",
    0.09
    [__
    0.09
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.