© 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. 8352
    Prev
    Next
    INDEX
    Explanations

    partition coefficient

    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
     generators
    -0.09
    ligen
    -0.07
    antage
    -0.07
    åħĥèĢģ
    -0.07
     generator
    -0.07
    ieee
    -0.07
    éĹ´éļĶ
    -0.06
    çģ«åĬĽ
    -0.06
    çļĦçģ«
    -0.06
     paving
    -0.06
    POSITIVE LOGITS
    transfer
    0.13
     transfer
    0.12
    转移
    0.12
     Transfer
    0.12
    -transfer
    0.11
     transfers
    0.11
     transferring
    0.11
    Transfer
    0.10
    转移åĪ°
    0.10
    _transfer
    0.09
    Activations Density 0.048%

    No Known Activations