© 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. 3906
    Prev
    Next
    INDEX
    Explanations

    shaft, button, key

    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
    ABCDEFGHI
    -0.07
    æľīçļĦæŶåĢĻ
    -0.07
    çī¹
    -0.06
     deadliest
    -0.06
    ä¸ĩè¾¾
    -0.06
     matrimonio
    -0.06
    çµ±åIJĪ
    -0.06
     Soh
    -0.06
    ÐĸÐĶ
    -0.06
    èŀįéĢļ
    -0.06
    POSITIVE LOGITS
    å¦Ĥåħ¶
    0.08
    .Doc
    0.07
    .Wrap
    0.07
    åIJijåħ¶
    0.07
    ican
    0.06
    amber
    0.06
    autop
    0.06
    æł¹æį®åħ¶
    0.06
    بÙĤ
    0.06
    -word
    0.06
    Activations Density 0.042%

    No Known Activations