© 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. 45367
    Prev
    Next
    INDEX
    Explanations

    family relations

    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
    笳
    -0.07
    çĭ©
    -0.07
    å¿ĥåĬ¨
    -0.06
    onio
    -0.06
    FLOW
    -0.06
    Ļ
    -0.06
    ryp
    -0.06
    먹
    -0.06
    ิว
    -0.06
    éĩĿ
    -0.06
    POSITIVE LOGITS
     intermediate
    0.08
    éĥ½ä¸İ
    0.08
    ä¹Łè·Ł
    0.08
     intermediary
    0.08
     intervention
    0.08
    ä¸ŃéĹ´
    0.08
     interven
    0.08
    interv
    0.07
     tre
    0.07
     intermedi
    0.07
    Activations Density 0.217%

    No Known Activations