© 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. 21978
    Prev
    Next
    INDEX
    Explanations

    document structure keywords

    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
    ologie
    -0.06
    éľĢåľ¨
    -0.06
     sorted
    -0.06
    enne
    -0.06
    ене
    -0.06
    ene
    -0.06
     famine
    -0.06
    elijk
    -0.06
    ellos
    -0.06
    ÙĪع
    -0.06
    POSITIVE LOGITS
    ebi
    0.08
    λεκ
    0.08
    jid
    0.07
    æĵİ
    0.07
    建æĸ°
    0.07
    avers
    0.07
    éľ¹
    0.07
    xid
    0.07
    æĺŁæľŁå¤©
    0.07
    éĻIJåĪ¶æ¶Īè´¹
    0.07
    Activations Density 0.005%

    No Known Activations