© 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. 4041
    Prev
    Next
    INDEX
    Explanations

    modem life agriculture

    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
    è¤
    -0.07
    ze
    -0.07
     –
    -0.07
    ÃĩA
    -0.07
    رÙĬات
    -0.06
    cratch
    -0.06
     inds
    -0.06
    ids
    -0.06
    éĶ¦æłĩ
    -0.06
    ius
    -0.06
    POSITIVE LOGITS
    çĶº
    0.09
    alités
    0.08
    ammans
    0.08
    omme
    0.08
     bum
    0.07
    ?'
    0.07
    尼奥
    0.07
    λλον
    0.07
    è¯Ļ
    0.07
     "'"
    0.07
    Activations Density 0.414%

    No Known Activations