© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 11853
    Prev
    Next
    INDEX
    Explanations

    file license

    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
    å¤ĩ
    -0.08
     irr
    -0.07
    å°±æĺ¯äºĨ
    -0.07
     Deck
    -0.06
    æľīä¸ĢèĤ¡
    -0.06
    æľīçļĦ
    -0.06
    frames
    -0.06
    åĪ°æł¡
    -0.06
    æģĥ
    -0.06
    çĪ±å°Ķ
    -0.06
    POSITIVE LOGITS
    常è¯Ĩ
    0.09
     Lesser
    0.07
    åħ¸æķħ
    0.07
    ä¹ĭæľĢ
    0.07
     autoria
    0.07
    åĩºå¤Ħ
    0.07
    odar
    0.07
    -origin
    0.07
    LETE
    0.07
     moz
    0.07
    Activations Density 0.003%

    No Known Activations