© 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. 18751
    Prev
    Next
    INDEX
    Explanations

    battle rating, cost, move speed

    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
    è´¯
    -0.06
    à¹Ģà¸ķิ
    -0.06
    æķ¦ä¿ĥ
    -0.06
    umbang
    -0.06
    æĺ¯ä¸ī
    -0.06
    缸åħ³çŁ¥è¯Ĩ
    -0.06
    jna
    -0.05
    trar
    -0.05
    -desc
    -0.05
    askan
    -0.05
    POSITIVE LOGITS
    afs
    0.07
     multic
    0.05
    åĩłæŃ¥
    0.05
     ens
    0.05
     owing
    0.05
    iable
    0.05
    åĽł
    0.05
    çħŀ
    0.05
    apis
    0.05
    åIJİåĽł
    0.05
    Activations Density 0.004%

    No Known Activations