© 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. 62462
    Prev
    Next
    INDEX
    Explanations

    files available online

    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
    enga
    -0.08
    kins
    -0.07
    atz
    -0.07
    Ãłm
    -0.07
    计
    -0.07
    idges
    -0.07
    reb
    -0.07
    çķĻé¦Ļ
    -0.07
    æĬĬå®ĥ
    -0.07
    äºĨçĦ¶
    -0.07
    POSITIVE LOGITS
    éļ¾æ±Ĥ
    0.07
    éĺij
    0.07
    çĥģ
    0.06
     nè
    0.06
    RA
    0.06
    大æĪĺ
    0.06
     szól
    0.06
     Scho
    0.06
    loff
    0.06
    /meta
    0.06
    Activations Density 1.483%

    No Known Activations