© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2792
    Prev
    Next
    INDEX
    Explanations

    help me or you

    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
    缸å®Ī
    -0.07
    oule
    -0.07
    locator
    -0.07
     Snowden
    -0.07
    lado
    -0.07
    弩
    -0.07
     Remark
    -0.07
    queta
    -0.07
    nok
    -0.07
     ActiveSupport
    -0.07
    POSITIVE LOGITS
    è¸ı
    0.07
    fab
    0.07
    ç±³å°Ķ
    0.07
    اÙĦÙħ
    0.07
    hre
    0.06
    çĭĤ
    0.06
    ix
    0.06
    ixa
    0.06
    _lazy
    0.06
    arp
    0.06
    Activations Density 0.001%

    No Known Activations