© 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. 38635
    Prev
    Next
    INDEX
    Explanations

    instructions and specified format

    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
    åݻ认è¯ģ
    -0.07
    稽
    -0.07
     believable
    -0.07
    ä¸įè¦ģè½»æĺĵ
    -0.07
    Thrown
    -0.07
    اÙħÙĨ
    -0.06
     Kass
    -0.06
    Cert
    -0.06
    illah
    -0.06
     ÑħваÑĤаеÑĤ
    -0.06
    POSITIVE LOGITS
    åħ·ä½ĵè¦ģæ±Ĥ
    0.10
    è¦ģæ±Ĥèĩªå·±
    0.10
    è¦ģæ±ĤçļĦ
    0.09
    çļĦè¦ģæ±Ĥ
    0.09
     format
    0.09
    è¦ģæ±Ĥ
    0.09
    format
    0.09
    æĮīè¦ģæ±Ĥ
    0.09
     specified
    0.09
    约å®ļçļĦ
    0.09
    Activations Density 0.032%

    No Known Activations