© 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. 18555
    Prev
    Next
    INDEX
    Explanations

    errors, listed, hard, required

    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
    ä¸ĭæĮ«
    -0.07
    quio
    -0.06
    mudah
    -0.06
    æĬķèµĦä»·åĢ¼
    -0.06
    AMOS
    -0.06
    ünchen
    -0.06
    chá
    -0.06
    .AdapterView
    -0.06
    vana
    -0.06
    ãĤ¿ãĥ¼
    -0.05
    POSITIVE LOGITS
    env
    0.06
    èĢ³çĽ®
    0.06
    å®Įåħ¨
    0.06
    éĽĨæĪIJ
    0.06
    æķ£
    0.06
     embodied
    0.06
     incentiv
    0.05
    大æĶ¾
    0.05
    ç³»ç»ŁéĽĨæĪIJ
    0.05
    org
    0.05
    Activations Density 0.005%

    No Known Activations