© 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. 47541
    Prev
    Next
    INDEX
    Explanations

    deficiency symptoms and withdrawal

    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
    Disallow
    -0.09
    ä¸įå¦ĤæĦı
    -0.08
    ÏĨα
    -0.08
    FRING
    -0.08
    SEQ
    -0.08
    imuth
    -0.08
    éĥ½å¸Ĥè¨Ģæĥħ
    -0.08
    orks
    -0.08
    örden
    -0.07
    estroy
    -0.07
    POSITIVE LOGITS
     manifestations
    0.10
     symptoms
    0.08
     signs
    0.08
     manifestation
    0.08
     manifests
    0.08
    轻度
    0.07
    åħ¸åŀĭçļĦ
    0.07
     manifest
    0.07
     mild
    0.07
     Manifest
    0.07
    Activations Density 0.182%

    No Known Activations