© 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. 8829
    Prev
    Next
    INDEX
    Explanations

    tumor and cancer cells

    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
     Thao
    -0.07
    verbind
    -0.07
    vern
    -0.07
    dorf
    -0.07
    å®ļæł¼
    -0.07
     ìĪľìĪĺ
    -0.07
    èļ¤
    -0.07
    uiten
    -0.07
    åħ¬åĭĻ
    -0.06
    debit
    -0.06
    POSITIVE LOGITS
     tumor
    0.14
     cancer
    0.12
    çĻĮç»Ĩèĥŀ
    0.12
     tumors
    0.11
    èĤ¿çĺ¤
    0.11
     cancers
    0.11
    çĻĮ
    0.10
     infiltr
    0.10
     onc
    0.10
     malignant
    0.10
    Activations Density 0.612%

    No Known Activations