© 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. 1663
    Prev
    Next
    INDEX
    Explanations

    child victim, prostitute, guy

    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
    -Semit
    -0.08
    egn
    -0.08
    ä¹Łåıªèĥ½
    -0.07
     بÙħجرد
    -0.07
     arguably
    -0.07
    irut
    -0.07
    æ¦Ħ
    -0.07
    æī¹åĩĨåIJİ
    -0.07
    åħįä¸įäºĨ
    -0.07
    ä¹Łæĺ¯éľĢè¦ģ
    -0.07
    POSITIVE LOGITS
     truth
    0.08
    åŃĺåľ¨çĿĢ
    0.07
    羣缸
    0.07
     thing
    0.06
    æľŁä¸Ń
    0.06
     ÑıкобÑĭ
    0.06
    à¸Īà¸ĩ
    0.06
    çĻ¾
    0.06
     truthful
    0.06
     dos
    0.06
    Activations Density 0.001%

    No Known Activations