© 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. 13652
    Prev
    Next
    INDEX
    Explanations

    cared about, awareness, commitment

    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
    apura
    -0.07
    olino
    -0.07
    çĽ¸å¯¹æ¯Ķè¾ĥ
    -0.07
    æľĢåIJİåľ¨
    -0.06
    _ASCII
    -0.06
    alach
    -0.06
     charismatic
    -0.06
     Bec
    -0.06
    _false
    -0.06
    åħ¼
    -0.06
    POSITIVE LOGITS
     cared
    0.09
     commitment
    0.09
    çĶ¨å¿ĥ
    0.08
    åĢ¼å¾Ĺä¿¡èµĸ
    0.08
    åľ¨ä¹İ
    0.08
    è¿ľ
    0.08
     cares
    0.08
     care
    0.08
    à¹ĥสà¹Īà¹ĥà¸Ī
    0.08
    åħ³å¿ĥ
    0.08
    Activations Density 0.128%

    No Known Activations