© 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. 51662
    Prev
    Next
    INDEX
    Explanations

    adding information or a point

    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
    adou
    -0.10
    æĸĩåĵ²
    -0.08
    ách
    -0.08
    slag
    -0.08
    ëĭĪëĭ¤
    -0.08
    aschen
    -0.08
    eselect
    -0.08
    ä¸ĭ称
    -0.08
    å¤ļæľĪçļĦ
    -0.08
    ixels
    -0.08
    POSITIVE LOGITS
    åĢ¼å¾Ĺ注æĦıçļĦæĺ¯
    0.10
     importantly
    0.09
    ue
    0.08
    åĢ¼å¾Ĺä¸ĢæıIJçļĦæĺ¯
    0.08
     there
    0.07
    ard
    0.07
    è¦ģ注æĦı
    0.07
    注æĦıåĪ°
    0.07
    å¦Ĥæŀľ
    0.07
     note
    0.07
    Activations Density 0.020%

    No Known Activations