© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20463
    Prev
    Next
    INDEX
    Explanations

    radio station network names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĢ§
    -0.06
     Nues
    -0.05
    ãĢĤ)
    -0.05
    åħ¥å¢ĥ
    -0.05
     «
    -0.05
    attr
    -0.05
    volu
    -0.05
     av
    -0.05
    å±ħ
    -0.05
    çĶŁç´ł
    -0.05
    POSITIVE LOGITS
    ilver
    0.06
    ستاÙĨÛĮ
    0.06
    ÒĽÑĭ
    0.05
    endas
    0.05
    راء
    0.05
    azz
    0.05
    armi
    0.05
    ä¹ĭ女
    0.05
    ovah
    0.05
    edi
    0.05
    Activations Density 0.018%

    No Known Activations