© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 37576
    Prev
    Next
    INDEX
    Explanations

    housing, frame, or casing

    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
    Negative Logits
    æıª
    -0.08
    èĵ¬åĭĥ
    -0.07
    å¾ĺå¾Ĭ
    -0.07
    èĩªè§ī
    -0.07
    çľ¼çľĭ
    -0.07
    纱å¸ĥ
    -0.06
     decipher
    -0.06
    rut
    -0.06
    peat
    -0.06
    æķıæĦŁ
    -0.06
    POSITIVE LOGITS
    -mounted
    0.09
    ernos
    0.08
     housing
    0.08
     mounting
    0.08
    å¼Ģ设æľī
    0.08
    åĪĨåĪ«ä¸İ
    0.08
    æĿIJè´¨
    0.08
    zel
    0.08
    éĿłå±±
    0.08
    ynchronously
    0.08
    Activations Density 0.413%

    No Known Activations