© 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. 43329
    Prev
    Next
    INDEX
    Explanations

    equivalent to

    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
    inari
    -0.08
     باÙĦتÙĨ
    -0.08
    幸
    -0.07
     defaultMessage
    -0.07
    edel
    -0.07
    èĵĭ
    -0.07
    asca
    -0.07
    .removeEventListener
    -0.07
    é²ľ
    -0.07
    åİŁæĸĩåĩºå¤Ħ
    -0.07
    POSITIVE LOGITS
    缸å½ĵäºİ
    0.21
    çŃīæķĪ
    0.18
     equivalent
    0.17
    å°±çĽ¸å½ĵäºİ
    0.16
     Equivalent
    0.15
    就好åĥı
    0.15
     ë§Īì¹ĺ
    0.15
     seolah
    0.14
    è§Ĩä½ľ
    0.14
     effectively
    0.14
    Activations Density 0.121%

    No Known Activations