© 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. 38573
    Prev
    Next
    INDEX
    Explanations

    ab, b, or batman

    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
    IPS
    -0.08
    åĽŃçļĦ
    -0.07
    asti
    -0.07
    ستاÙĨÛĮ
    -0.07
    峨
    -0.07
    Ñİ
    -0.07
    azion
    -0.07
    IVA
    -0.07
    rena
    -0.07
    entai
    -0.07
    POSITIVE LOGITS
    èĦĤ
    0.07
    critical
    0.06
    èĦĤè´¨
    0.06
    å°Ħ
    0.06
    подоб
    0.06
    ÙĦÙģ
    0.06
    许åı¯è¯ģ
    0.06
    cred
    0.06
    è¿ĩéĩį
    0.06
    ä¹ĭå®Ŀ
    0.06
    Activations Density 0.002%

    No Known Activations