© 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. 30570
    Prev
    Next
    INDEX
    Explanations

    medical, biological, and political contexts

    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
    ibr
    -0.07
    hek
    -0.06
    æĶĺ
    -0.06
    离
    -0.06
    HE
    -0.06
    åĪĨå¤ĸ
    -0.06
    roid
    -0.06
     muri
    -0.06
     bro
    -0.06
    ills
    -0.06
    POSITIVE LOGITS
    nip
    0.08
    .Dir
    0.08
     fotoc
    0.08
    åı¯æĢķçļĦ
    0.08
    ighted
    0.08
    éĩij丹
    0.08
    rlen
    0.07
    weiler
    0.07
    geno
    0.07
    оÑĩе
    0.07
    Activations Density 0.029%

    No Known Activations