© 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. 7772
    Prev
    Next
    INDEX
    Explanations

    capacity, size, expansion

    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
    庸
    -0.08
    æĺ¯åħ¨çIJĥ
    -0.07
    zzle
    -0.07
    è¿ĩå¢ĥ
    -0.07
    .Parse
    -0.07
    weighted
    -0.07
    odb
    -0.07
     desemp
    -0.06
     дÑĥ
    -0.06
     subt
    -0.06
    POSITIVE LOGITS
    æī©å®¹
    0.13
    容纳
    0.13
    容éĩı
    0.12
    容éĩıçļĦ
    0.12
     вмеÑģÑĤ
    0.12
     expansion
    0.11
     capacity
    0.11
     capacities
    0.10
     size
    0.10
    æī©åħħ
    0.10
    Activations Density 0.041%

    No Known Activations