© 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. 7660
    Prev
    Next
    INDEX
    Explanations

    immune response

    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
    é¢ł
    -0.07
    çĪ¶åŃIJ
    -0.07
    anity
    -0.07
    éĻįåİĭ
    -0.06
    Change
    -0.06
    oleon
    -0.06
     complying
    -0.06
    oard
    -0.06
    change
    -0.06
    éŃĤ
    -0.06
    POSITIVE LOGITS
     defenses
    0.12
     responses
    0.11
    éĺ²å¾¡
    0.10
     иммÑĥн
    0.10
     defense
    0.10
     immune
    0.10
     response
    0.10
    response
    0.09
     Responses
    0.09
     responders
    0.09
    Activations Density 0.320%

    No Known Activations