© 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. 64459
    Prev
    Next
    INDEX
    Explanations

    secondary / subordinate / last / part / benefit

    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
    ç»ı缸åħ³éĥ¨éŨæī¹åĩĨ
    -0.08
    ]{
    -0.07
    ugo
    -0.07
    å°Ķ夫
    -0.07
    zimmer
    -0.07
    ëıħ
    -0.07
    èĻ½çĦ¶æ²¡æľī
    -0.07
    ilde
    -0.07
     ev
    -0.07
     Ged
    -0.07
    POSITIVE LOGITS
    次è¦ģ
    0.13
     secondary
    0.13
    åıªæĺ¯
    0.11
    secondary
    0.10
    Secondary
    0.10
     subordinate
    0.10
     Secondary
    0.10
     incidental
    0.10
     merely
    0.09
     sekund
    0.09
    Activations Density 0.080%

    No Known Activations